3D-VCD reduces hallucinations in 3D-LLM embodied agents by contrasting predictions from original and distorted 3D scene representations at inference time.
Uni3d-llm: Unifying point cloud perception, generation and editing with large language models
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
In this paper, we introduce Uni3D-LLM, a unified framework that leverages a Large Language Model (LLM) to integrate tasks of 3D perception, generation, and editing within point cloud scenes. This framework empowers users to effortlessly generate and modify objects at specified locations within a scene, guided by the versatility of natural language descriptions. Uni3D-LLM harnesses the expressive power of natural language to allow for precise command over the generation and editing of 3D objects, thereby significantly enhancing operational flexibility and controllability. By mapping point cloud into the unified representation space, Uni3D-LLM achieves cross-application functionality, enabling the seamless execution of a wide array of tasks, ranging from the accurate instantiation of 3D objects to the diverse requirements of interactive design. Through a comprehensive suite of rigorous experiments, the efficacy of Uni3D-LLM in the comprehension, generation, and editing of point cloud has been validated. Additionally, we have assessed the impact of integrating a point cloud perception module on the generation and editing processes, confirming the substantial potential of our approach for practical applications.
fields
cs.CV 4years
2026 4representative citing papers
ELSA3D introduces elastic semantic anchoring via sparse anchor tokens and a scale-aware octree tokenizer to unify 3D generation and captioning at reduced computational cost.
Pointy, a lightweight transformer trained on 39k point clouds, outperforms larger foundation models trained on 200k+ samples and nears SOTA from million-sample multimodal models.
SGSoft introduces a template-guided pipeline that fuses semantic and geometric features to learn dense correspondences across deformable 3D shapes with claimed SOTA generalization and real-time efficiency.
citing papers explorer
-
3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding
3D-VCD reduces hallucinations in 3D-LLM embodied agents by contrasting predictions from original and distorted 3D scene representations at inference time.
-
ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation
ELSA3D introduces elastic semantic anchoring via sparse anchor tokens and a scale-aware octree tokenizer to unify 3D generation and captioning at reduced computational cost.
-
Pointy - A Lightweight Transformer for Point Cloud Foundation Models
Pointy, a lightweight transformer trained on 39k point clouds, outperforms larger foundation models trained on 200k+ samples and nears SOTA from million-sample multimodal models.
-
SGSoft: Learning Fused Semantic-Geometric Features for 3D Shape Correspondence via Template-Guided Soft Signals
SGSoft introduces a template-guided pipeline that fuses semantic and geometric features to learn dense correspondences across deformable 3D shapes with claimed SOTA generalization and real-time efficiency.