REVIEW 5 cited by
Contrastive Gaussian Clustering: Weakly Supervised 3D Scene Segmentation
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
abstract
We introduce Contrastive Gaussian Clustering, a novel approach capable of provide segmentation masks from any viewpoint and of enabling 3D segmentation of the scene. Recent works in novel-view synthesis have shown how to model the appearance of a scene via a cloud of 3D Gaussians, and how to generate accurate images from a given viewpoint by projecting on it the Gaussians before $\alpha$ blending their color. Following this example, we train a model to include also a segmentation feature vector for each Gaussian. These can then be used for 3D scene segmentation, by clustering Gaussians according to their feature vectors; and to generate 2D segmentation masks, by projecting the Gaussians on a plane and $\alpha$ blending over their segmentation features. Using a combination of contrastive learning and spatial regularization, our method can be trained on inconsistent 2D segmentation masks, and still learn to generate segmentation masks consistent across all views. Moreover, the resulting model is extremely accurate, improving the IoU accuracy of the predicted masks by $+8\%$ over the state of the art. Code and trained models will be released soon.
Forward citations
Cited by 5 Pith papers
-
DreamGrasp: Zero-Shot 3D Multi-Object Reconstruction from Partial-View Images for Robotic Manipulation
A zero-shot pipeline reconstructs per-instance 3D geometry in cluttered scenes from two partial RGB views by combining diffusion-based score distillation with learned instance features and text-guided refinement.
-
Efficient multi-view training for 3D Gaussian Splatting
Training 3D Gaussian Splatting with multiple images per iteration, using partial rendering and a 3D-aware SSIM loss, improves novel-view synthesis quality over single-view training.
-
Enhancing LLM Training via Spectral Clipping
SPECTRA improves LLM pretraining via post-clipping of update spectral norms and optional pre-clipping of gradient spikes, framed as Composite Frank-Wolfe regularization.
-
Hi-LSplat: Hierarchical 3D Language Gaussian Splatting
Hi-LSplat trains language-augmented 3D Gaussians with a three-level semantic tree and instance/part contrastive losses, improving open-vocabulary 3D segmentation and localization on eight datasets.
-
The ALMA-QUARKS Survey: III. Clump-to-core fragmentation and search for high-mass starless cores
In 139 infrared-bright massive protoclusters, ALMA resolves 1562 cores whose separations are much smaller than the Jeans length, and finds only two candidate high-mass starless cores.
Discussion (0). Continue with ORCID to comment.