13 papers
WorldRecon: Generative Multi-View Mesh Reconstruction for Large-Scale 3D World
Mengchen Zhang, Yang Li, Chunshi Wang +2
Reconstructing complete, high-quality meshes of large-scale scenes from unposed multi-view images requires faithful geometric grounding while plausibly completing surfaces that are…
Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing
Junliang Ye, Kenkun Liu, Guocun Wang +13
Recent advances in image generation have demonstrated the potential of unified multimodal models that integrate understanding, generation, and editing. However, unified 3D modeling…
WorldClaw: Agentic 3D Open-World Generation at Scale
Chunchao Guo, Jinpeng Li, Yang Li +1
Generating large-scale, freely explorable 3D worlds from open-ended text remains challenging because a system must jointly maintain global spatial coherence, rich local content, an…
PolyFlow: Continuous Topology Embedding Flow Matching for Artist-style Mesh Generation
Chunshi Wang, Haohan Weng, Junliang Ye +9
Autoregressive Transformers dominate high-quality mesh generation by producing artist-worthy topologies, yet their inherent sequential decoding induces substantial computational ov…
PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World
Yunhan Yang, Chunshi Wang, Junliang Ye +7
Synthesizing physics-grounded 3D assets is a critical bottleneck for interactive virtual worlds and embodied AI. Existing methods predominantly focus on static geometry, overlookin…
HY3D-Bench: Generation of 3D Assets
Team Hunyuan3D, :, Bowen Zhang +22
While recent advances in neural representations and generative models have revolutionized 3D content creation, the field remains constrained by significant data processing bottlene…
MoCA: Mixture-of-Components Attention for Scalable Compositional 3D Generation
Zhiqi Li, Wenhuan Li, Tengfei Wang +8
Compositionality is critical for 3D object and scene generation, but existing part-aware 3D generation methods suffer from poor scalability due to quadratic global attention costs…
Part-X-MLLM: Part-aware 3D Multimodal Large Language Model
Chunshi Wang, Junliang Ye, Yunhan Yang +6
We introduce Part-X-MLLM, a native 3D multimodal large language model that unifies diverse 3D tasks by formulating them as programs in a structured, executable grammar. Given an RG…
ArtUV: Artist-style UV Unwrapping
Yuguang Chen, Xinhai Liu, Yang Li +4
UV unwrapping is an essential task in computer graphics, enabling various visual editing operations in rendering pipelines. However, existing UV unwrapping methods struggle with ti…
P3-SAM: Native 3D Part Segmentation
Changfeng Ma, Yang Li, Xinhao Yan +7
Segmenting 3D assets into their constituent parts is crucial for enhancing 3D understanding, facilitating model reuse, and supporting various applications such as part generation.…
X-Part: high fidelity and structure coherent shape decomposition
Xinhao Yan, Jiachen Xu, Yang Li +8
Generating 3D shapes at part level is pivotal for downstream applications such as mesh retopology, UV mapping, and 3D printing. However, existing part-based generation methods ofte…
Auto-Regressive Surface Cutting
Yang Li, Victor Cheung, Xinhai Liu +8
Surface cutting is a fundamental task in computer graphics, with applications in UV parameterization, texture mapping, and mesh decomposition. However, existing methods often produ…
GUAVA: Generalizable Upper Body 3D Gaussian Avatar
Dongbin Zhang, Yunfei Liu, Lijian Lin +5
Reconstructing a high-quality, animatable 3D human avatar with expressive facial and hand motions from a single image has gained significant attention due to its broad application…