REVIEW 7 cited by
Segment Any Mesh
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We propose Segment Any Mesh, a novel zero-shot mesh part segmentation method that overcomes the limitations of shape analysis-based, learning-based, and contemporary approaches. Our approach operates in two phases: multimodal rendering and 2D-to-3D lifting. In the first phase, multiview renders of the mesh are individually processed through Segment Anything to generate 2D masks. These masks are then lifted into a mesh part segmentation by associating masks that refer to the same mesh part across the multiview renders. We find that applying Segment Anything to multimodal feature renders of normals and shape diameter scalars achieves better results than using only untextured renders of meshes. By building our method on top of Segment Anything, we seamlessly inherit any future improvements made to 2D segmentation. We compare our method with a robust, well-evaluated shape analysis method, Shape Diameter Function, and show that our method is comparable to or exceeds its performance. Since current benchmarks contain limited object diversity, we also curate and release a dataset of generated meshes and use it to demonstrate our method's improved generalization over Shape Diameter Function via human evaluation. We release the code and dataset at https://github.com/gtangg12/samesh
Forward citations
Cited by 7 Pith papers
-
BANG: Dividing 3D Assets via Generative Exploded Dynamics
A diffusion-based method that generates smooth exploded-view sequences of 3D objects, enabling part-level decomposition, control, and reassembly.
-
Articulated Object Reconstruction from Rest-State Observation
Rest2Art reconstructs part geometry and joint parameters of openable objects from a single closed-state observation by co-refining vision-language and segmentation outputs on a mesh and fitting joint models to video-d...
-
EditVerse3D: High-Quality 3D Object Editing with Region-Aware Learning
An end-to-end 3D editing framework achieves high-fidelity local edits from coarse bounding boxes and 2D image prompts using region-aware loss reweighting and a large-scale parts-derived training dataset.
-
SimFoundry: Modular and Automated Scene Generation for Policy Learning and Evaluation
SimFoundry automates zero-shot real-to-sim scene generation from video, producing digital twins and cousins that enable policy training with 0.911 mean Pearson correlation to real-world results and 17-40% success gain...
-
DexVLG: Dexterous Vision-Language-Grasp Model at Scale
DexVLG is a vision-language model trained on 170 million simulated dexterous grasps that generates hand poses aligned with language instructions about which part of an object to grasp.
-
Efficient Part-level 3D Object Generation via Dual Volume Packing
From a single image, a 3D latent diffusion model generates all parts of an object at once by packing the part structure into two non-overlapping volumes.
-
GeoSAM2: Unleashing the Power of SAM2 for 3D Part Segmentation
A prompt-controllable 3D part segmentation method that adapts SAM2 with LoRA and geometry fusion on rendered normal and point maps, then back-projects multi-view masks to the mesh.
Discussion (0). Continue with ORCID to comment.