mlsanityData to 14 Oct 2026

EPS3D: End-to-End Feed-Forward 3D Panoptic Segmentation

arXiv 2606.08980 ↗First posted 8 Jun 2026cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

This paper introduces EPS3D, a new end-to-end feed-forward framework for open-vocabulary 3D panoptic segmentation. Unlike existing methods relying on additional preprocessing, we design an end-to-end architecture, with a distillation-based training strategy on diverse 3D scenes to predict 3D-aware semantic and instance features from multi-view images, improving 3D consistency and avoiding error accumulation. We further propose a mutual enhancement module to enforce inherent semantic-instance consistency. By aligning semantics within instances (Ins2Sem) and refining instance features with semantic guidance (Sem2Ins), we achieve more coherent 3D scene understanding. Ultimately, EPS3D outperforms SOTA baselines on two benchmarks (e.g., +13% mIoU for semantics on Replica) with high efficiency (e.g., 1s per scene), supporting tasks like robotic manipulation and 3D scene editing.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 73 of its 80 references that are in the map. First posted on arXiv 8 Jun 2026.

Builds on

73 of 80 references.

References · 73

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023Segment Anythingcited by 8,234
  3. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  4. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  5. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  6. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  7. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  8. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  9. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  10. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  11. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
  12. 2020Neural Sparse Voxel Fieldscited by 959
38 more
  1. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 764
  2. 2022Language-driven Semantic Segmentationcited by 717
  3. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 684
  4. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 667
  5. 2023Point Transformer V3: Simpler, Faster, Strongercited by 589
  6. 2021Extract Free Dense Labels from CLIPcited by 583
  7. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 566
  8. 2023LERF: Language Embedded Radiance Fieldscited by 543
  9. 2023LangSplat: 3D Language Gaussian Splattingcited by 415
  10. 2023Gaussian Grouping: Segment and Edit Anything in 3D Scenescited by 393
  11. 2022Decomposing NeRF for Editing via Feature Field Distillationcited by 371
  12. 2023Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fieldscited by 364
  13. 2025π3: Permutation-Equivariant Visual Geometry Learningcited by 319
  14. 2024ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulationcited by 315
  15. 2023Reconstructing Hands in 3D with Transformerscited by 306
  16. 2024No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Imagescited by 248
  17. 2025AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Viewscited by 243
  18. 20196-DOF GraspNet: Variational Grasp Generation for Object Manipulationcited by 242
  19. 2023Language Embedded 3D Gaussians for Open-Vocabulary Scene Understandingcited by 208
  20. 2024GaussianPro: 3D Gaussian Splatting with Progressive Propagationcited by 200
  21. 2021Point-Based Neural Rendering with Per-View Optimizationcited by 190
  22. 2023Semantic-SAM: Segment and Recognize Anything at Any Granularitycited by 185
  23. 2024WildGaussians: 3D Gaussian Splatting in the Wildcited by 152
  24. 2024OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understandingcited by 145
  25. 2022Neural Wavelet-domain Diffusion for 3D Shape Generationcited by 132
  26. 2024Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collectionscited by 117
  27. 2024Pixel-GS: Density Control with Pixel-aware Gradient for 3D Gaussian Splattingcited by 113
  28. 2025FastVGGT: Training-Free Acceleration of Visual Geometry Transformercited by 98
  29. 2023Language Embedded Radiance Fields for Zero-Shot Task-Oriented Graspingcited by 91
  30. 2024Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splattingcited by 82
  31. 2024GaussianGrasper: 3D Language Gaussian Splatting for Open-vocabulary Robotic Graspingcited by 78
  32. 2024Large Spatial Model: End-to-end Unposed Images to Semantic 3Dcited by 73
  33. 2024OpenNeRF: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel Viewscited by 69
  34. 2024Analytic-Splatting: Anti-Aliased 3D Gaussian Splatting via Analytic Integrationcited by 67
  35. 2024Texture-GS: Disentangling the Geometry and Texture for 3D Gaussian Splatting Editingcited by 47
  36. 2024InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perceptioncited by 35
  37. 2022Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshescited by 34
  38. 2024N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fieldscited by 34

50 most cited of 73 All 73 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026CNS-Edit++: Category-Agnostic 3D Editing with Coupled Neural Shape Representationcited by 0
  2. 2026LEGO: Leveled Language Gaussian Splattingcited by 0
  3. 2026Every View Counts: View-Consistent Panoptic Quality for Multi-view Panoptic Segmentationcited by 0