3D Shape Modeling and Analysis

Latest papers

• SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation

  Tianjiao Yu, Xinzhuo Li, Yifan Shen, Ying Shen, Kiet A. Nguyen, Adheesh Sunil Juvekar, Ismini Lourentzou · 2 October 2026

  High-resolution 3D generation increasingly relies on voxel latents and multi-stage pipelines that first predict active structure and then synthesize local geometry. While effective, this design fragments continuous surfaces into many local tokens, inflates generation cost, and often weakens topologi…

• SPHERE: Adaptive VR Indoor Scene Generation via LLM-Enhanced Spatial Preference Learning and Human-in-the-Loop RL

  Hyeonmin Lee, Zheng Wei, Kyungmin Kwon, Jumin Seo, Jiwon Park, Hayoung Oh · 2 October 2026

  While Large Language Models (LLMs) advance 3D indoor scene synthesis, current pipelines fail to retain user-specific preferences across sessions, making immersive authoring a repetitive and physically fatiguing process. We present SPHERE, an adaptive VR generation framework that transforms isolated …

• SPOON: Towards Coherent Compositional 3D Scene Generation from Uncalibrated Multi-view Images

  Guibiao Liao, Mochu Xiang, Heng Li, Ken Deng, Zijie Wang, Guanbin Li, Ping Tan, Shenghua Gao, Yizhou Yu · 1 October 2026

  Compositional 3D scene generation aims to recover complete 3D object shapes and their spatial arrangement from visual observations. Recent image-conditioned 3D generators provide strong priors for producing high-quality object geometry, making the generation of complex scenes increasingly practical.…

• MeshOctave generates meshes via cascading resolution transitions

  Junkai Lin, Tianhao Zhao, Hang Long, Huipeng Guo, Jielei Zhang, Youjia Zhang, Jiale Xu, Wenbing Li, Rendong Liang, Jozef Hladk\'y, Matthias Nie{\ss}ner, Yuanming Hu, Wei Yang · 1 October 2026

  Generating compact, artist-style meshes with explicit topology typically relies on autoregressive models which incur prohibitive sequential per-token costs, or continuous flow models that depend on heuristic connectivity decoders. Next-scale generation paradigms offer a compelling alternative by ena…

• AdaOcc: Adaptive 3D Occupancy Prediction for Embodied Tasks

  Jinglong Wang, Yunjie Wang, Zhiyang Zhang, Jiawei He, Ye Yuan, Bo Qiu, Jing Zhang · 1 October 2026

  Embodied tasks demand accurate, flexible, and semantically rich 3D scene representations. 3D semantic occupancy is well suited to this requirement, as it can model holistic 3D spaces by encoding geometric occupancy along with semantic categories. However, existing occupancy prediction methods strugg…

• HIGS: Hierarchical Implicit Grids for Joint Geometric and Semantic Scene Understanding

  Hanwen Cao, Wenqiang Wu, Kuang-Ting Tu, Mathias Otnes, Jeffrey Delmerico, Rui Wang, Yulun Tian, Nikolay Atanasov · 1 October 2026

  Neural implicit representations have had a significant impact on scene reconstruction by enabling robots to build continuous, differentiable, and high-fidelity 3D maps. Most existing works focus on geometric reconstruction and lack semantic information for high-level spatial understanding and task p…

• CoDimRecon: Agentic Reconstruction of Sim-Ready 3D Scenes with Deformable Curves, Surfaces, and Volumes

  Shuzhao Xie, Lelin Wang, Guying Lin, Zhi Wang, Minchen Li · 30 September 2026

  Reconstructing simulation-ready 3D scenes from real-world observations enables robotics, gaming, and immersive applications, yet existing methods largely assume rigid objects. This leaves an important gap for deformables, whose simulation-ready geometry depends on dimensionality (curves, surfaces, o…

• VGGT-Diff: Visual Geometry Meets Diffusion for Sparse-View Novel View Synthesis

  Kangjie Chen, Xiangyu Li, Dongbin Zhang, Chaoda Zheng, Shijia Chen, Jinhao Deng, Hongbin Lin, Choo Sin Wai, Minqi Wang, Minghao Yang, Dake Zhong, Guorui Song, Yu Zhang, Xianming Liu, Boyang Wang · 29 September 2026

  We present VGGT-Diff, a geometry-routed multi-view diffusion model for sparse-view novel view synthesis. Existing novel view synthesis (NVS) methods face a fundamental trade-off: reconstruction-based approaches preserve observed geometry but struggle to synthesize unseen regions, while diffusion-bas…

• GraphWrit3R: End-to-End 3D Scene Graph Writing

  Luka Milivojevic, Nikola Popovic, Sayan Deb Sarkar, Sebastian Koch, Iro Armeni, Luc Van Gool, Danda Pani Paudel · 28 September 2026

  3D scene graphs provide a structured representation of complex environments by encoding objects, their semantic attributes, and the spatial and functional relationships between them. Current approaches for 3D scene graph generation suffer from several fundamental limitations. They rely on complex mu…

• M3GD: Multi-Modal Multi-View Geometric Diffusion for Camera--LiDAR Novel View Synthesis

  Yang Zhou, Jiuhong Xiao, Shizhao Ye, Long Quang, Carlos Nieto-Granda, Giuseppe Loianno · 25 September 2026

  Robotic novel view synthesis (NVS) must recover both visual appearance and metric 3D structure, yet most generative NVS methods rely only on images, overlooking LiDAR, a complementary sensor common on robotic platforms. We present M3GD, a Camera--LiDAR multimodal representation for generative NVS th…

• ToCo-Mesh: Topology-Consistent Dynamic Mesh Reconstruction via Adaptive Tessellation and Surface-Aligned 2DGS

  Chuanjin Fan, Wenjie Chang, Aibing Li, Bingzhou Wang, Wenfei Yang, Tianzhu Zhang · 25 September 2026

  Reconstructing dynamic meshes with consistent topology from multi-view temporal images remains a challenge. Existing approaches typically face a dilemma between fine-scale shape recovery and topological stability. Frame-by-frame extraction methods capture fine details but break vertex correspondence…

• SplatLabel: Pseudo-Labelling through 4D Gaussian Splatting

  Nitya Nanvani, Andras Palffy, Holger Caesar · 25 September 2026

  While 2D Vision Foundation Models offer a pathway to automate 3D semantic pseudo-labelling, translating these priors into robust 3D representations typically requires complex heuristics or multi-model ensembles. We introduce SplatLabel, an automated pipeline that leverages a 4D Gaussian representati…

• OREO: Fidelity Alignment in 3D Generation via On-the-fly Rendering-Editing Optimization

  Zhiyuan Ma, Wenbo Hu, Wang Zhao, Pengfei Wang, Ying Shan, Lei Zhang · 25 September 2026

  Despite recent advancements in 3D generation, models often struggle to produce assets with high visual fidelity. To bridge this gap, we propose OREO, an alignment framework that enhances the realism of 3D generators by leveraging rich 2D diffusion priors. Instead of relying on static datasets, OREO …

• M-plicits: Neural Implicit Surfaces via Nested Multiscale Residuals

  Vin\'icius da Silva, Isabelle Melo, Matheus Bessa, Guilherme Schardong, Luiz Schirmer, Andr\'e Ara\'ujo, Nuno Gon\c{c}alves, H\'elio Lopes, Alberto Raposo, Luiz Velho, Tiago Novello · 25 September 2026

  Encoding input coordinates with sinusoidal functions into multi-layer perceptrons (MLPs) has proven effective for implicit neural representations (INRs) of surfaces defined as zero-level sets. However, existing methods often struggle to balance training efficiency, rendering speed, and noise robustn…

• PePESeg3D: Perception Prior Enhances Multi-Scale Segmentation for 3D Gaussian Splatting

  Sungjae Choi, Seunghee Koh, Junmo Kim · 25 September 2026

  Recent advancements in 3D Gaussian Splatting (3DGS) have extended its capabilities to multi-scale segmentation. Existing methods reconstruct a scene with Gaussian primitives and learn multi-scale segmentation features separately, which leaves the geometry unaware of semantic structure and the featur…

• TopoGS: Topology-Aware Anchor Feature Aggregation for Large-Scale 3D Gaussian Splatting

  Wei Zhang, Shiqiang Gong, Shengkai Yu, Zeyu Wang, Clement Mallet, Zhitong Xiong, Qi Wang · 24 September 2026

  Octree-based 3D Gaussian Splatting organizes anchors into multi-level hierarchies for level-of-detail rendering, but features at different levels are typically optimized independently, leaving the octree topology underused during feature learning. We observe that uniform cross-level aggregation prod…

• DMM-Align: Closed-Loop Optimization for 2D-3D Registration with Dual-Role Diffusion

  Chongjian Wang, Junjie Gao · 24 September 2026

  2D-3D registration remains brittle in challenging scenarios such as low overlap, occlusion, repetitive structures, and severe cross-modal ambiguity. A key reason is that existing methods improve representation learning, correspondence estimation, or pose computation in isolation, while the dominant …

• Fusion-Aware Direct 3D Gaussian Generation with Structured Patch Latent Flows

  Yizhao Wang, Jingbo Wang, Guantao Zhang · 24 September 2026

  Class-guided 3D object generation is important for intelligent content creation, virtual environments, and digital asset design. Although 3D Gaussian Splatting (3DGS) offers an explicit and render-efficient representation, directly generating 3D Gaussian objects is difficult because Gaussian primiti…

• NeuralSRNF: Neural Square Root Normal Fields for the Statistical Shape Analysis and Generation of Nonrigid 3D and 4D Objects

  Awais Nizamani, Hamid Laga, Guanjin Wang, Farid Boussaid, Mohammed Bennamoun, Anuj Srivastava · 24 September 2026

  We introduce NeuralSRNF, a novel framework for the statistical shape analysis and generation of genus-zero 3D and 4D objects that undergo nonrigid deformations. Traditional methods rely on complex and computationally expensive nonlinear elastic metrics that measure bending and stretching. Recent adv…

• Hybrid Gaussians for Robust Open-Vocabulary 3D Segmentation with Multi-View Object Association and Boundary Refinement

  Xueqi Qiu, Yueming Sun, Tianyu Zhang, Yuxuan Xia, Yang Long · 24 September 2026

  Open-vocabulary 3D segmentation localizes objects from free-form text queries, but remains challenging in real image sequences: incomplete or noisy 2D supervision destabilizes multi-view identity assignment, while full-scene semantic learning weakens object-level discriminability. We introduce Hybri…

• CODA: Depth-Aligned Scene Completion and Object Decomposition from a Single RGB-D Image

  Dongwon Son, Junhyek Han, Yoontae Cho, Minseok Lee, Hong-seok Choi, Jiwook Choi, Hyungjin Kim, Beomjoon Kim · 23 September 2026

  Robots operating safely in cluttered everyday environments often need to infer scene geometry from partial observations. Methods that detect objects in 2D and reconstruct them independently struggle in such scenes: a missed object is never reconstructed, a merged detection can fuse two objects, and …

• EMERGE: Resolution-Agnostic Point Cloud Generation with Equivariant Graph-Based Diffusion

  Ilias Mitsouras, Nikolaos Chaidos, Giorgos Stamou, Athanasios Voulodimos · 23 September 2026

  Point cloud generation has emerged as a crucial task for accurately capturing and reproducing the complexity of the physical world. However, existing generative approaches, predominantly relying on Transformers and Variational Autoencoders (VAEs), frequently ignore the continuous, non-grid topologie…

• GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation

  Jiahao Lu, Minghao Yin, Wenbo Hu, Hengyu Liu, Wang Zhao, Sai-Kit Yeung, Ying Shan, Yuan Liu · 22 September 2026

  We present a compact geometry-native latent space as a shared foundation for perception and generation. Visual generators can produce photorealistic frames without preserving a consistent 3D scene. We argue that this is not only a modeling problem but also a representation problem: generators typica…

• ZVeC: A Zero-Shot Framework for Instance-Level Vehicle Extraction and Generative Point Cloud Completion

  Daisy Li, Kyle Gao, Quanyun Wu, Boris Jutzi, John S. Zelek, Jonathan Li · 22 September 2026

  LiDAR point clouds acquired in underground environments exhibit severe geometric incompleteness due to occlusions and limited sensor viewpoints, making reliable point cloud completion challenging without large supervised datasets. We propose ZVeC, a zero-shot, instance-driven framework that reformul…

• Mira-Scene: Pixel-Aligned Layouts for Generative 3D Scene

  Yang-Tian Sun, Tianjia Liu, Zehuan Huang, Yi-Hua Huang, Xiaoyang Lyu, Ziyi Yang, Zi-Xin Zou, Yuan-Chen Guo, Yan-Pei Cao, Xiaojuan Qi · 22 September 2026

  Single-image 3D object generation can now produce high-fidelity assets, yet accurately placing them into a coherent scene layout remains an open challenge. A central difficulty lies in how object layout is represented. Holistic methods absorb placement into a scene-level generation process, sacrific…