mmiranda nvidia style edits to surgical scene reconstruction #1329
Conversation
Signed-off-by: meg miranda <[email protected]>
| - **Initialization:** Multi-frame point cloud (~30,000-50,000 points from all frames) | ||
| - **Renderer:** gsplat library (CUDA-accelerated differentiable rasterization) | ||
| - **Renderer:** `gsplat` library (CUDA-accelerated differentiable rasterization) | ||
| - **Spherical Harmonics:** Degree 3 (16 coefficients per gaussian for view-dependent color) |
There was a problem hiding this comment.
what is "degree 3"?
Greptile SummaryThis PR applies NVIDIA style guide edits to the surgical scene reconstruction README, improving clarity and organization throughout the document. Key changes include:
Issue found: Lines 54-56 contain a duplicate command and malformed code block that will break markdown rendering. Confidence Score: 4/5
Important Files Changed
Sequence DiagramsequenceDiagram
participant User
participant CLI as HoloHub CLI
participant Docker
participant Train as Training Pipeline
participant Render as Rendering Pipeline
User->>CLI: ./holohub run surgical_scene_recon train
CLI->>Docker: Build/Start Container
Docker->>Train: Execute gsplat_train.py
Train->>Train: Load EndoNeRF Dataset
Train->>Train: Initialize Multi-frame Point Cloud
Train->>Train: Coarse Stage Training
Train->>Train: Fine Stage Training with Deformation
Train->>Docker: Save Checkpoint to output/
Docker-->>CLI: Training Complete
CLI-->>User: Display Training Results
User->>CLI: ./holohub run surgical_scene_recon render
CLI->>Docker: Start Container with Checkpoint
Docker->>Render: Initialize Holoscan Pipeline
Render->>Render: EndoNeRFLoaderOp (Load Poses)
Render->>Render: GsplatLoaderOp (Load Checkpoint)
Render->>Render: GsplatRenderOp (Apply Deformation & Render)
Render->>Render: HolovizOp (Real-time Visualization)
Render->>Render: ImageSaverOp (Optional Save)
Render-->>User: Display Real-time 3D Reconstruction
|
WalkthroughRewrote and reorganized the surgical_scene_recon README: clarified scope and intro, renamed and expanded features, detailed dataset contents and setup, expanded model and training descriptions (3D Gaussian Splatting, temporal deformation), refined Quick Start/training/rendering steps, added outputs/logging, requirements, testing notes, and standardized citations. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 minutes 🚥 Pre-merge checks | ✅ 2✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. 📜 Recent review detailsConfiguration used: Organization UI Review profile: CHILL Plan: Pro 📒 Files selected for processing (1)
🚧 Files skipped from review as they are similar to previous changes (1)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Fix all issues with AI agents
In @applications/surgical_scene_recon/README.md:
- Line 23: The README contains a grammatical typo: change the phrase "uses
cases" to "use cases" on the affected sentence (line with "It is ideal for uses
cases, such as:") so it reads "It is ideal for use cases, such as:"; update that
exact wording in applications/surgical_scene_recon/README.md.
📜 Review details
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
applications/surgical_scene_recon/README.md
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Greptile Review
🔇 Additional comments (3)
applications/surgical_scene_recon/README.md (3)
3-5: Clarify intent of the two opening paragraphs.Lines 3 and 5 now convey nearly identical information—both describe real-time 3D surgical reconstruction with Gaussian Splatting and temporal deformation. After restructuring to emphasize the end-to-end pipeline, one of these appears redundant.
Verify whether both paragraphs serve a distinct purpose (e.g., detailed vs. summary) or if one should be removed for clarity.
96-107: Dataset setup instructions are clear and complete.The restructured dataset setup (lines 96–107) with numbered steps, inline code blocks, and explicit path placeholders is an improvement. The symlink warning on Line 109 is important context that is appropriately positioned.
41-41: All external links and documentation references in the README are properly formatted and valid. The relative path to the HoloHub glossary (../../README.md#Glossary) is correct, and the glossary section exists in the root README. The file appropriately references and uses HoloHub glossary terms for project-specific locations as required.
There was a problem hiding this comment.
line 120/126 the title of Model. What model are we talking here?
…to the training section, the duplication bothered me Signed-off-by: meg miranda <[email protected]>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> Signed-off-by: megnvidia <[email protected]>
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
There was a problem hiding this comment.
Greptile Overview
Greptile Summary
This PR applies NVIDIA style guide edits to the surgical scene reconstruction README, improving formatting, organization, and readability.
Key improvements:
- Enhanced document structure with clearer section headings and better organization
- Improved Quick Start instructions with numbered lists and better code block formatting
- Standardized terminology and punctuation throughout
- Added more descriptive section titles (e.g., "Pulling Soft Tissues Dataset" instead of "Data")
- Refined technical descriptions and explanations
Issues found:
- Line 23: Typo "uses cases" should be "use cases"
- Line 52: Inaccurate term "virtual surgical training" should be "model training"
- Line 143: Incorrect technical description of Temporal Deformation Network references MRI data interpolation instead of surgical tissue deformation
- Line 5: Redundant sentence that duplicates the introduction
- Line 135: Inconsistent capitalization of "Gaussian"
Confidence Score: 3/5
- This PR has some style improvements but contains a critical technical inaccuracy and several smaller issues that should be fixed
- Score reflects that while most changes are beneficial style edits, there is a significant technical error (incorrect TGN model description on line 143), a typo, and inaccurate terminology that could confuse users
- The README.md file needs attention, specifically line 143 which contains incorrect technical information about the Temporal Deformation Network
Important Files Changed
File Analysis
| Filename | Score | Overview |
|---|---|---|
| applications/surgical_scene_recon/README.md | 3/5 | Style guide edits to improve clarity and consistency; found typo, inaccurate terminology, and incorrect technical description |
Sequence Diagram
sequenceDiagram
participant Author as PR Author
participant File as README.md
participant Review as Documentation Review
participant User as End User
Author->>File: Apply NVIDIA style guide edits
Author->>File: Restructure sections and headings
Author->>File: Improve Quick Start formatting
Author->>File: Enhance dataset documentation
Author->>File: Standardize terminology
Note over File: Introduced typo: "uses cases"
Note over File: Added inaccurate term: "virtual surgical training"
Note over File: Added incorrect TGN description
Note over File: Redundant sentence on line 5
Review->>File: Identify style improvements
Review->>File: Detect typo on line 23
Review->>File: Find terminology issue on line 52
Review->>File: Catch technical error on line 143
Review->>File: Note inconsistencies
File->>User: Improved readability & organization
File->>User: Better Quick Start instructions
File->>User: Clearer dataset setup steps
Note over Review: Requires fixes before merge
| - **Output:** Real-time 3D tissue reconstruction without surgical instruments | ||
|
|
||
| ### Use Cases | ||
| It is ideal for use cases, such as: |
There was a problem hiding this comment.
typo: "uses cases" should be "use cases"
| It is ideal for use cases, such as: | |
| It is ideal for use cases, such as: |
| ### Step 4: Dynamic Rendering with a Trained Model | ||
|
|
||
| After training completes, visualize your results in real-time: | ||
| After training completes, to visualize your results in real-time, run the surgical render: |
There was a problem hiding this comment.
"run the surgical render" is awkward - not a standard technical term
| After training completes, to visualize your results in real-time, run the surgical render: | |
| After training completes, to visualize your results in real-time: |
Note: If this suggestion doesn't match your team's coding style, reply to this and let me know. I'll remember it for next time!
| - **Output:** Deformed position, scale, rotation, and opacity changes | ||
| - **Training:** Two-stage process (coarse: static, fine: with deformation) | ||
| - **Inference:** Direct PyTorch (no conversion, full precision) | ||
| - Architecture: 3D Gaussian with learned position, scale, rotation, opacity, and color |
There was a problem hiding this comment.
inconsistent capitalization - "Gaussian" should be capitalized consistently with the rest of the document
| - Architecture: 3D Gaussian with learned position, scale, rotation, opacity, and color | |
| - Architecture: 3D Gaussians with learned position, scale, rotation, opacity, and color |
There was a problem hiding this comment.
Greptile Overview
Greptile Summary
This PR applies NVIDIA style guide edits to the surgical scene reconstruction README, improving formatting, organization, and readability throughout the documentation.
Major changes:
- Restructured introduction section with clearer feature descriptions
- Enhanced Quick Start section with numbered lists and better command formatting
- Improved dataset documentation with detailed download and setup instructions
- Standardized section headings and terminology throughout
- Reformatted code blocks and citation sections for consistency
Issues found:
- Line 143 contains a critical technical inaccuracy: describes the Temporal Deformation Network as a "Temporal Generative Network (TGN)" for "missing MRI data," which is incorrect for this surgical endoscopy application
- Line 5 introduces redundant content that duplicates line 3
- Inconsistent code block indentation in Step 3 (line 54)
- Terminology errors: "3D Gaussian" should be "3D Gaussians" (line 135), "Gaussian functions" should be "Gaussians" (line 243)
Confidence Score: 3/5
- This PR requires revisions before merging due to technical inaccuracies in the documentation
- Score of 3 reflects that while most style improvements are beneficial, there is a critical technical error at line 143 that misrepresents the Temporal Deformation Network functionality, terminology errors that could confuse readers, and formatting inconsistencies that should be addressed before merging
- Pay close attention to line 143 (incorrect TGN description), line 135 (terminology), and line 243 (terminology)
Important Files Changed
File Analysis
| Filename | Score | Overview |
|---|---|---|
| applications/surgical_scene_recon/README.md | 3/5 | Style guide improvements with some formatting inconsistencies and one critical technical inaccuracy about the Temporal Deformation Network (line 143) |
Sequence Diagram
sequenceDiagram
participant User
participant PR as Pull Request Review
participant Doc as README.md
participant StyleGuide as NVIDIA Style Guide
User->>PR: Submit style edits PR
PR->>Doc: Apply formatting changes
Doc->>Doc: Restructure sections
Doc->>Doc: Improve Quick Start formatting
Doc->>Doc: Standardize terminology
Doc->>Doc: Enhance readability
PR->>StyleGuide: Validate against style guide
StyleGuide-->>PR: Check formatting consistency
StyleGuide-->>PR: Check technical accuracy
Note over Doc: Issues found:<br/>- Redundant line 5<br/>- Inconsistent indentation<br/>- Inaccurate TGN description<br/>- Terminology errors
PR->>User: Return review feedback
|
|
||
| This application demonstrates real-time 3D surgical scene reconstruction by combining **Holoscan SDK** for high-performance streaming, **3D Gaussian Splatting** for neural 3D representation, and **temporal deformation networks** for accurate modeling of dynamic tissue. | ||
|
|
||
| Real-time 3D surgical scene reconstruction using Gaussian Splatting in a Holoscan streaming pipeline with temporal deformation for accurate tissue modeling. |
There was a problem hiding this comment.
This line is redundant and duplicates the content from line 3. It should be removed to avoid repetition.
| Real-time 3D surgical scene reconstruction using Gaussian Splatting in a Holoscan streaming pipeline with temporal deformation for accurate tissue modeling. |
| ### Training Process | ||
| - Temporal Deformation Network model | ||
| Temporal Generative Network (TGN) model generates data that integrates bidirectional deformation estimation with temporal prediction to interpolate missing MRI data and forecast future frames. |
There was a problem hiding this comment.
This description of the Temporal Deformation Network is inaccurate. It mentions "Temporal Generative Network (TGN)" generating "missing MRI data", but this application is for surgical endoscopy (not MRI), and the network performs real-time deformation (not data interpolation/forecasting). This description appears to be copied from an unrelated medical imaging context.
The description should match the actual functionality described in lines 146-150, which correctly describes the HexPlane-based deformation network.
| - **Output:** Deformed position, scale, rotation, and opacity changes | ||
| - **Training:** Two-stage process (coarse: static, fine: with deformation) | ||
| - **Inference:** Direct PyTorch (no conversion, full precision) | ||
| - Architecture: 3D Gaussian with learned position, scale, rotation, opacity, and color |
There was a problem hiding this comment.
3D Gaussian should be 3D Gaussians (plural) to match the original description and be technically correct, as the model uses multiple Gaussian primitives.
| - Architecture: 3D Gaussian with learned position, scale, rotation, opacity, and color | |
| - Architecture: 3D Gaussians with learned position, scale, rotation, opacity, and color |
| - Gaussian Splatting Model | ||
| ### Temporal Deformation Network | ||
| Each portion of the application makes use of different aspects of the Gaussian Splatting Model. |
There was a problem hiding this comment.
This sentence is vague and doesn't add meaningful information. What "different aspects" does it refer to? Consider removing or making it more specific.
Note: If this suggestion doesn't match your team's coding style, reply to this and let me know. I'll remember it for next time!
There was a problem hiding this comment.
yes a vague lead in -- twas my attempt to try to add some explanation for what the bullet list is trying to be. Ideal would be adding other words that help make the bullets make sense, but I need some feedback on what the list is trying to accomplish
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Fix all issues with AI agents
In @applications/surgical_scene_recon/README.md:
- Around line 126-150: The opening sentence of the Temporal Deformation Network
(TGN) description incorrectly references MRI data; update the sentence that
currently reads "Temporal Generative Network (TGN) model generates data that
integrates bidirectional deformation estimation with temporal prediction to
interpolate missing MRI data and forecast future frames" to instead state that
the TGN interpolates missing endoscopic frames and forecasts future frames using
EndoNeRF endoscopic data (RGB images + stereo depth + camera poses), keeping the
rest of the TGN details (HexPlane 4D grid, MLP decoder,
input/output/training/inference) unchanged.
🧹 Nitpick comments (1)
applications/surgical_scene_recon/README.md (1)
156-157: Minor grammar refinement: "where" clause construction.Lines 156–157 use grammatically awkward constructions:
- "The Coarse Stage where the application learns..."
- "The Fine Stage where a temporal deformation network model is added..."
These read more naturally as "In the Coarse Stage, the application learns..." or "The Coarse Stage: the application learns..."
This is a minor stylistic improvement; the meaning is clear as written.
✏️ Proposed improvements
- 1. The Coarse Stage where the application learns the base static Gaussian models without deformation. - 2. The Fine Stage where a temporal deformation network model is added for dynamic tissue modeling. + 1. **Coarse Stage:** The application learns the base static Gaussian models without deformation. + 2. **Fine Stage:** A temporal deformation network model is added for dynamic tissue modeling.
📜 Review details
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
applications/surgical_scene_recon/README.md
🔇 Additional comments (2)
applications/surgical_scene_recon/README.md (2)
12-28: Past comment resolved: Use cases typo fixed.Line 23 correctly shows "use cases" (was flagged as "uses cases" in previous review). Feature additions ("Tool Removal," "End-to-End Training") and restructured use cases are clear and well-organized.
131-139: Past comment resolved: "Degree 3" terminology clarified.Line 138 now explains "Degree 3 (16 coefficients per gaussian for view-dependent color)" which directly addresses the previous comment asking "what is 'degree 3'?" The explanation is clear and technical.
|
My intuition is telling me that the later half of this README has some content that we might not really care to keep, but I can't make those choices without discussion and feedback from a subject matter expert. I did more formatting changes on this article than I had originally intended. These readme's span the gray are between user guide and readme content. I probably leaned more toward user guide formatting style with this. We may not want that. |
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> Signed-off-by: megnvidia <[email protected]>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> Signed-off-by: megnvidia <[email protected]>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> Signed-off-by: megnvidia <[email protected]>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> Signed-off-by: megnvidia <[email protected]>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> Signed-off-by: megnvidia <[email protected]>
| - **Output:** Deformed position, scale, rotation, and opacity changes | ||
| - **Training:** Two-stage process (coarse: static, fine: with deformation) | ||
| - **Inference:** Direct PyTorch (no conversion, full precision) | ||
| The Temporal Deformation Network deforms 3D Gaussians over time to model dynamic tissue movement during surgery. |
There was a problem hiding this comment.
incorrect description for Temporal Deformation Network - mentions MRI data and TGN which are not part of this surgical endoscopy application
| The Temporal Deformation Network deforms 3D Gaussians over time to model dynamic tissue movement during surgery. | |
| The Temporal Deformation Network uses a HexPlane-based 4D spatiotemporal grid representation to model tissue deformation over time in surgical scenes. |
There was a problem hiding this comment.
ok I think this part is going to continue to make the AI mad. The AI and myself are both attempting to add clarity but I think we need an actual subject matter expert to weigh in. Please help us.
| ./holohub run surgical_scene_recon train | ||
| ``` | ||
| ./holohub run surgical_scene_recon train | ||
| ``` |
There was a problem hiding this comment.
inconsistent indentation - code block is indented but other code blocks in Quick Start section are not
| ./holohub run surgical_scene_recon train | |
| ``` | |
| ./holohub run surgical_scene_recon train | |
| ``` | |
| ```bash | |
| ./holohub run surgical_scene_recon train |
Note: If this suggestion doesn't match your team's coding style, reply to this and let me know. I'll remember it for next time!
There was a problem hiding this comment.
Greptile Overview
Greptile Summary
This PR applies style guide edits to the surgical scene reconstruction README, improving formatting, organization, and readability. However, it introduces a critical factual error in the Temporal Deformation Network description.
Key Issues:
- Critical: Line 142 contains incorrect description stating the model "integrates bidirectional deformation estimation with temporal prediction to interpolate missing MRI data and forecast future frames" - this application uses surgical endoscopy video for tissue reconstruction, not MRI data
- Terminology inconsistency: Line 134 changed "3D Gaussians" (plural) to "3D Gaussian" (singular), but the architecture uses multiple Gaussian primitives (the original plural form was correct)
Positive Changes:
- Improved section organization and heading structure
- Better formatting with numbered lists and consistent indentation
- Clearer Quick Start instructions with step-by-step guidance
- Enhanced dataset setup documentation with verification steps
- More detailed training pipeline explanation
Confidence Score: 2/5
- This PR has a critical factual error that misrepresents the application's functionality and must be corrected before merging
- Score reflects one critical factual error (TGN description mentions MRI instead of surgical video) and one terminology inconsistency (Gaussians plural→singular). While the style improvements are beneficial, the factual inaccuracy about the model's purpose is misleading and needs correction
- applications/surgical_scene_recon/README.md requires attention - specifically line 142 (critical factual error) and line 134 (terminology correction)
Important Files Changed
File Analysis
| Filename | Score | Overview |
|---|---|---|
| applications/surgical_scene_recon/README.md | 2/5 | Style guide edits to README with one critical factual error about Temporal Deformation Network (mentions MRI instead of surgical video) and one terminology inconsistency (singular vs plural Gaussians) |
Sequence Diagram
sequenceDiagram
participant User
participant PR as Pull Request
participant README as README.md
participant Review as Code Review
User->>PR: Submit style guide edits
PR->>README: Apply formatting changes
Note over README: Reorganize sections<br/>Update headings<br/>Improve clarity
PR->>README: Update model descriptions
Note over README: ⚠️ Incorrect TGN description<br/>(MRI vs surgical video)
PR->>README: Standardize terminology
Note over README: ⚠️ Change "Gaussians" to "Gaussian"<br/>(plural to singular)
Review->>README: Identify factual error
Review->>README: Identify terminology issue
Review->>User: Request corrections
| ### Temporal Deformation Network | ||
| - Temporal Deformation Network model | ||
There was a problem hiding this comment.
Description incorrect - mentions MRI data and forecast future frames, but this application uses surgical endoscopy video for tissue reconstruction, not MRI
| The Temporal Deformation Network enables dynamic scene modeling by deforming the base Gaussian representations over time to accurately capture tissue movement and deformation during surgery. |
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> Signed-off-by: megnvidia <[email protected]>
| ```bash | ||
| ./holohub run surgical_scene_recon train | ||
| ``` | ||
| ./holohub run surgical_scene_recon train | ||
| ``` |
There was a problem hiding this comment.
syntax: Duplicate command - line 54 and 55 both contain ./holohub run surgical_scene_recon train
| ```bash | |
| ./holohub run surgical_scene_recon train | |
| ``` | |
| ./holohub run surgical_scene_recon train | |
| ``` | |
| ```bash | |
| ./holohub run surgical_scene_recon train |
| - Architecture: 3D Gaussians with learned position, scale, rotation, opacity, and color | ||
| - Architecture: 3D Gaussian with learned position, scale, rotation, opacity, and color |
There was a problem hiding this comment.
syntax: Duplicate Architecture entry - same item listed twice with different singular/plural forms ("3D Gaussians" vs "3D Gaussian")
| - Architecture: 3D Gaussians with learned position, scale, rotation, opacity, and color | |
| - Architecture: 3D Gaussian with learned position, scale, rotation, opacity, and color | |
| - Architecture: 3D Gaussians with learned position, scale, rotation, opacity, and color |
Signed-off-by: meg miranda <[email protected]>
| ./holohub run surgical_scene_recon train | ||
| ``` | ||
| ./holohub run surgical_scene_recon train | ||
| ``` |
There was a problem hiding this comment.
syntax: duplicate command and broken code block - line 54 is duplicated on line 55, and the closing backticks are on the wrong indentation level
| ./holohub run surgical_scene_recon train | |
| ``` | |
| ./holohub run surgical_scene_recon train | |
| ``` | |
| ```bash | |
| ./holohub run surgical_scene_recon train |
There was a problem hiding this comment.
Greptile Overview
Greptile Summary
This PR applies NVIDIA style guide edits to the surgical scene reconstruction README, improving documentation clarity and structure.
Key Changes:
- Restructured introduction to lead with application purpose
- Expanded Quick Start section with numbered steps and clearer instructions
- Enhanced dataset download and setup instructions with better formatting
- Added detailed training pipeline documentation
- Standardized formatting for citations and code blocks
- Improved section organization (e.g., "Data" → "Pulling Soft Tissues Dataset")
Issue Found:
- Line 54-55: Duplicate command
./holohub run surgical_scene_recon trainwith incorrect indentation in the training code block
Confidence Score: 4/5
- This PR is safe to merge after fixing the duplicate command in the training instructions
- The PR contains style guide improvements to documentation with good restructuring and enhanced clarity. However, there is one syntax error (duplicate command line 54-55) that needs correction. The changes are documentation-only with no code logic changes, making this low-risk overall.
- applications/surgical_scene_recon/README.md requires attention to fix the duplicate command in Step 3
Important Files Changed
File Analysis
| Filename | Score | Overview |
|---|---|---|
| applications/surgical_scene_recon/README.md | 4/5 | Style guide updates with one syntax error: duplicate command in code block (line 54-55) |
Sequence Diagram
sequenceDiagram
participant Dev as Developer
participant PR as Pull Request
participant Doc as README.md
participant User as End User
Dev->>Doc: Apply NVIDIA style guide edits
Dev->>Doc: Restructure sections for clarity
Dev->>Doc: Expand Quick Start instructions
Dev->>Doc: Add detailed training pipeline info
Dev->>Doc: Standardize formatting and citations
Note over Dev,Doc: Duplicate command added by mistake
Dev->>PR: Submit changes
PR->>User: Documentation improvements available
User->>Doc: Read enhanced documentation
User->>Doc: Follow improved instructions
| ./holohub run surgical_scene_recon train | ||
| ``` | ||
| ./holohub run surgical_scene_recon train |
There was a problem hiding this comment.
duplicate command with incorrect indentation
| ./holohub run surgical_scene_recon train | |
| ``` | |
| ./holohub run surgical_scene_recon train | |
| ./holohub run surgical_scene_recon train |
2 participants
style guide edits to the surgical scene reconstruction readme.
Summary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings.