REVIEW 15 cited by
SAMPart3D: Segment Any Part in 3D Objects
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
3D part segmentation is a crucial and challenging task in 3D perception, playing a vital role in applications such as robotics, 3D generation, and 3D editing. Recent methods harness the powerful Vision Language Models (VLMs) for 2D-to-3D knowledge distillation, achieving zero-shot 3D part segmentation. However, these methods are limited by their reliance on text prompts, which restricts the scalability to large-scale unlabeled datasets and the flexibility in handling part ambiguities. In this work, we introduce SAMPart3D, a scalable zero-shot 3D part segmentation framework that segments any 3D object into semantic parts at multiple granularities, without requiring predefined part label sets as text prompts. For scalability, we use text-agnostic vision foundation models to distill a 3D feature extraction backbone, allowing scaling to large unlabeled 3D datasets to learn rich 3D priors. For flexibility, we distill scale-conditioned part-aware 3D features for 3D part segmentation at multiple granularities. Once the segmented parts are obtained from the scale-conditioned part-aware 3D features, we use VLMs to assign semantic labels to each part based on the multi-view renderings. Compared to previous methods, our SAMPart3D can scale to the recent large-scale 3D object dataset Objaverse and handle complex, non-ordinary objects. Additionally, we contribute a new 3D part segmentation benchmark to address the lack of diversity and complexity of objects and parts in existing benchmarks. Experiments show that our SAMPart3D significantly outperforms existing zero-shot 3D part segmentation methods, and can facilitate various applications such as part-level editing and interactive segmentation.
Forward citations
Cited by 15 Pith papers
-
EditFlow3D: Automated Local Editing of 3D Assets with Trajectory Preservation
Mask-guided differential flow with a soft preservation loss enables training-free local 3D editing that keeps unedited regions close to the source asset.
-
GaussianSelector: Lightweight Human-Guided Object Selection in 3D Gaussian Splatting with Graph Optimization
A training-free graph-cut method selects 3D objects from Gaussian splatting scenes using sparse user scribbles, reaching 92.2 mIoU on NVOS with three interaction views.
-
MeshFM: 2D Features Are All You Need for 3D Shape Understanding
A feedforward network trained only on 2D foundation-model features predicts rotation-robust, general-purpose 3D mesh features that work zero-shot for segmentation, correspondence, and deformation.
-
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.
-
Harnessing Generative Image Models for Training-Free Primitive Shape Abstraction
Prompted generative image models plus classical superquadric fitting yield category-agnostic 3D primitive abstractions with the lowest Chamfer distance on HumanPrim and Toys4K using 5–9 parts.
-
Utonia: Toward One Encoder for All Point Clouds
Utonia pretrains one Point Transformer encoder jointly on indoor, outdoor, object, and video-lifted point clouds, and shows cross-domain transfer and downstream gains.
-
PatchAlign3D: Local Feature Alignment for Dense 3D Shape Understanding
A feed-forward 3D encoder aligning patch-level point-cloud features with part-name text embeddings achieves state-of-the-art zero-shot 3D part segmentation, surpassing multi-view rendering pipelines by large margins o...
-
PhysChoreo: Physics-Controllable Video Generation with Part-Aware Semantic Grounding
A two-stage framework that predicts per-part material properties from a single image and uses editable physics simulation to guide video generation.
-
MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh
MeshLLM improves LLM-based 3D mesh understanding and generation through primitive decomposition, a 1500k+ sample dataset, and topology-focused training strategies.
-
AutoPartGen: Autogressive 3D Part Generation and Discovery
AutoPartGen generates 3D objects as a sequence of latent-space parts, conditioning each new part on previously generated parts, and reports state-of-the-art part completion on PartObjaverse-Tiny.
-
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.
-
Auto-Regressive Surface Cutting
SeamGPT generates artist-style mesh cutting seams as auto-regressively predicted quantized 3D line segments, improving UV unwrapping and part segmentation.
-
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.
-
PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers
PartCrafter generates several separable 3D part meshes at once from a single image by fine-tuning a pretrained 3D diffusion transformer with part identity tokens and local-global attention.
-
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). Sign in to comment.