Latest 3D Vision & NeRFs Research Papers

The newest 3D Vision & NeRFs papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks 3D Vision & NeRFs so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.

Recent papers

• SonoWorld4D: From One Video to a 4D Audio-Visual Scene via Diffusion Synchronization
  Derong Jin, Xiyi Chen, Ming C. Lin, Ruohan Gao · arXiv · Oct 29, 2026

  Recent progress in visual scene generation has extended beyond static 3D scenes toward the more challenging problem of generating dynamic 4D scenes from minimal input. However, sound, despite being intrinsically coupled with dynamic objects…

• L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory
  Jinhyeok Choi, JoungBin Lee, Jongmin Lee, Minkyeong Jeon et al. · arXiv · Oct 29, 2026

  Interactive world models generate visual content conditioned on user actions, yet maintaining spatial consistency over long-horizon exploration in real time remains challenging. Existing approaches rely on either temporal context or explici…

• HairDeck: Animation-Ready Stylized Hair Cards from a Single Image
  Yuze He, Yixiang Wei, Wang Zhao, Chuhao Chen et al. · arXiv · Oct 29, 2026

  The hair of stylized characters in games and avatars is built from hair cards: artist-placed ribbons whose geometry is the visible hair, animated by spring bones. Existing image-based methods produce realistic hair or a single fused mesh, w…

• CrossWeave: Cross-Modal Scene and Instance Retrieval from Sparse 2D-3D Alignment
  Aadith Warrier, Gnana Prakash Punnavajhala, Siddharth Tourani, Muhammad Haris Khan et al. · arXiv · Oct 29, 2026

  Cross-modal scene and instance retrieval aims to retrieve a corresponding 3D environment or object given query 2D images, serving as a foundational mechanism for spatial reasoning in robotics and AR/VR. Existing methods achieve this by lear…

• LucidLyra: Feed-Forward Generative 3D Scene Reconstruction and Joint Understanding via Multi-Task Distillation
  Oliver Hahn, Rodrigo Marcuzzi, Sangeetha Grama Srinivasan, Alessandro Burzio et al. · arXiv · Oct 29, 2026

  We present LucidLyra, a framework that makes generatively reconstructed 3D scenes directly queryable for semantics and instances in a feed-forward manner from video latents. While generative 3D reconstruction can synthesize virtual environm…

• Uncertainty-aware Coarse-to-Fine Main Pancreatic Duct Segmentation for Width Measurement in 3D MRCP
  Zipei Zhang, Jaakko Sahlsten, Mikko Saukkoriipi, Johanna Ronkainen et al. · arXiv · Oct 29, 2026

  Assessment of the main pancreatic duct (MPD) from volumetric magnetic resonance cholangiopancreatography (MRCP) scans is an essential task for ductal dilatation diagnosis and pancreatic cancer analysis. However, manual assessment is affecte…

• EPC-RawDC: Equivariant Physics Constrained 3D Diffusion with Raw Data Consistency for CBCT to CT Image Synthesis
  Alzahra Altalib, Chunhui Li, Alessandro Perelli · arXiv · Oct 29, 2026

  Cone beam computed tomography (CBCT) is widely used for image guided and adaptive radiotherapy, but scatter, noise, reconstruction artifacts, and inaccurate Hounsfield units limit its quantitative use. Recent diffusion approaches for CBCT t…

• MLLM-GS: Multimodal Large Language Model Prior-Guided Fast Novel View Synthesis in Extreme Environments
  Zhiliang Wu, Xinye Zheng, Kun Li, Fei Wang et al. · arXiv · Oct 29, 2026

  Novel view synthesis (NVS) in degraded scenes aims to reconstruct 3D scenes from multi-view observations affected by various degradations, and to generate clear and photorealistic images at unseen viewpoints. Despite recent advances, existi…

• PhysAg3D: Bridging 3D Generative and Agentic Models for High-Fidelity and Physically-Interactive Assets
  Bi'an Du, Fanpeng Meng, Jiemin Fang, Chen Yang et al. · arXiv · Oct 29, 2026

  Generating interactive 3D assets from a single image requires realistic appearance, fidelity to the depicted object, and plausible physical behavior. Yet detailed geometry alone does not determine how an object should move or deform. We int…

• LiDAR-SHIELD: A Fully Dockerized Adversarial Robustness Assessment Framework for LiDAR-Based 3D Perception Models
  Alexandros Gkillas, Ioulia Kapsali, Christos Anagnostopoulos, Aris S. Lalos · arXiv · Oct 29, 2026

  LiDAR-based 3D perception underpins autonomous driving and robotics, yet deploying these models safely requires stress-testing them against adversarial inputs before real-world use. Although state-of-the-art adversarial attacks exist, their…

• On the Compact Discontinuous Galerkin Method for Polytopal Meshes
  Mattia Corti, Sergio Gómez · SIAM Journal on Scientific ... · Oct 28, 2026

  Abstract. The compact discontinuous Galerkin method was introduced by Peraire and Persson in (SIAM J. Sci. Comput., 30, 1806–1824, 2008). In this work, we present the stability and convergence analysis for the [Formula: see text]-version of…

• Technical development and implementation of 3D‐QALAS on a 1.5T MR‐Linac for the brain: A prospective R‐IDEAL stage 0/1 technology development report
  Lucas B. McCullum, Ashley Harrington, Natalie A. West, Grace Nehring et al. · Journal of Applied Clinical... · Oct 28, 2026

  BACKGROUND: Quantitative relaxometry of the brain on the integrated MRI / linear accelerator (MR-Linac) at high isotropic reconstructed resolution is currently limited due to prohibitively long scan times and limited field-of-views. PURPOSE…

• Honeycomb-Surfels: Compact Hexagonal Primitives for Efficient Scene Rendering and Reconstruction
  Prakhar Kaushik, Soumava Paul, Alan Yuille · arXiv · Oct 27, 2026

  Novel view synthesis and 3D reconstruction have advanced rapidly with radiance fields and splatting, yet their memory and computational demands limit their use in resource-constrained settings. We introduce Hexels: novel planar hexagonal su…

• CTBakeGS: training-free baking of photorealistic CT volume renderings into 3D Gaussian splats
  Haruki Fukuda, Constantin Lux, Wolf Schweitzer, Tadashi Hosoya et al. · arXiv · Oct 27, 2026

  Photorealistic volume rendering of computed tomography (CT) may convey anatomy intuitively, but it needs the CT data, dedicated software and a powerful graphics processor. Three-dimensional Gaussian splatting (3DGS) displays photorealistic …

• ScIntBench: Physical Interaction Plausibility in 3D Scene Generation
  Wendi Ying, Daochang Liu, Leonid Sigal, Ajmal Saeed Mian · arXiv · Oct 27, 2026

  Existing evaluations of text-conditioned 3D indoor scene generation largely emphasize semantic fidelity and physical validity at rest, leaving interaction-time physical reliability insufficiently assessed. To address this gap, we introduce …

• Zhengrong-Spatial-Aware 1.0: Advancing 3D Multimodal Intelligence
  Yu Zhang, Xiaogang Wang, Yuhang Cheng, Jingrui Li et al. · arXiv · Oct 27, 2026

  This report presents the implementation and validation of two end-to-end multimodal adaptation pipelines for 3D-aware visual question answering on a custom spatial dataset. The first pipeline fine-tunes HiSpatial-3B, which augments RGB obse…

• 3D-SceneQ: Empowering 3D LLM With Query-Guided Adaptive Pruning and Multi-Modal Feature Enhancement
  Yongqi Shan, Lu Zhang, Jiazuo Yu, Yunzhi Zhuge et al. · TMM · Oct 27, 2026

  Current 3D scene understanding pipelines typically concatenate vast numbers of 3D object tokens with text tokens and feed the resulting sequence to a Large Language Model (LLM). However, existing 3D-LLMs for scene understanding encounter tw…

• FastBEVFusion: Simple Multi-Modal Fusion for 3D Object Detection at 50 FPS
  Tom Sanitz, Emre Gülsoylu, Simone Frintrop, Christian Wilms · arXiv · Oct 27, 2026

  Reliable real-time 3D object detection based on LiDAR and camera data is critical for safety in autonomous driving, where systems must accurately perceive their surroundings with minimal latency. Many state-of-the-art systems achieve high-q…

• GCSR-OCC: Geometry Calibration and Semantic Routing for Open-Vocabulary Occupancy Prediction
  Bohua Wang, Congyang Zhao, Tianxiong Lv, Chenxu Zhao et al. · arXiv · Oct 27, 2026

  Open-vocabulary 3D occupancy prediction represents scene geometry and semantics in a unified voxel grid, enabling recognition beyond predefined categories. One approach reconstructs scenes with 3D Gaussians and converts them into voxel occu…

• Learning to Code the World: Harness Evolution for Compositional 3D Reconstruction
  Haoyu Yao, Chenguo Lin, Ruize Du, Yadong Mu · arXiv · Oct 27, 2026

  Reconstructing editable and compositional 3D scenes from a real image requires jointly reasoning about geometry, object structure, and spatial relationships. We introduce SceneEvolve, a framework that represents 3D scenes as executable code…

• GraftRay: Physically Based Mesh Insertion into Gaussian Splatting Scenes via Path Tracing
  Jinxin Ai, Matthias Niessner · arXiv · Oct 27, 2026

  Inserting virtual objects into scenes reconstructed via 2D or 3D Gaussian Splatting (2DGS/3DGS) is a key capability for content creation, AR, and synthetic data generation. However, realistic insertion requires the object to be seamlessly l…

• GPA-VGGT: Geometry-Preserving Acceleration of VGGT
  Muyeol Sung, Jangwon Kim, Jongwoo Lim · arXiv · Oct 27, 2026

  Feed-forward geometry models such as VGGT recover camera parameters, depth maps, and point maps from one to hundreds of views in a single forward pass, making them powerful backbones for multi-view 3D perception. However, VGGT's global atte…

• LingGS: Decoupling Feed-Forward Geometry Prediction from Camera Tracking for High-Fidelity Gaussian SLAM
  Da Li, Yihan Zang, Ivan Viola, Zeyu Wang et al. · arXiv · Oct 27, 2026

  Achieving high-quality reconstruction and responsive camera tracking remains challenging for monocular RGB Gaussian splatting SLAM under a limited optimization budget. We present an online system that addresses this challenge by combining l…

• 3D Reconstruction of Nanoparticle Distribution in Tumor Spheroids With Volume Electron Microscopy
  Davide Bottone, Lukas R. H. Gerken, Sebastian F. M. Habermann, José Marı́a Mateos et al. · Small · Oct 27, 2026

  A bstract Spatially resolved characterization of nanomaterial (NM) distribution within cellular ultrastructure is essential for understanding NM fate and activity in biological systems. Volume electron microscopy (vEM) is uniquely positione…

• FL4N: Feed-forward Latent Model for 4D Novel View Synthesis
  Eunbeen Hong, Hyeonseo Yu, Honggyu An, Jooho Son et al. · arXiv · Oct 26, 2026

  4D novel view synthesis (NVS) aims to render dynamic scenes across viewpoints and timestamps, which requires jointly inferring 3D structure and temporal dynamics. Existing monocular feed-forward methods often rely on explicit 4D Gaussian re…

• Does VGGT Know What It Does Not Know?
  Adityan Thirumani Srinivasan, David Nordström · arXiv · Oct 26, 2026

  Feed-forward 3D reconstruction models such as VGGT regress cameras and geometry in a single forward pass, but they report no uncertainty for the camera poses they predict: an incorrect relative pose looks no different from a correct one. We…

• VidEdit3D: Flexible 3D Gaussian Editing with Video Diffusion
  Yanming Yang, Chenxi Song, Tong Zhao, Juntao Xu et al. · arXiv · Oct 26, 2026

  Recent advancements in text-guided 3D editing, particularly with 3D Gaussian Splatting (3DGS), have shown promise but still lag behind the flexibility of 2D editing tools. Existing methods face a critical trade-off between preserving multi-…

• VPR-Space: A Benchmark for Visual Place Recognition in Space Analog Domains
  Richard Fechner, Peer Neubert · arXiv · Oct 26, 2026

  Visual Place Recognition (VPR) is an important means for loop closure detection in visual Simultaneous Localization and Mapping (SLAM). While state-of-the-art VPR and SLAM approaches excel in urban and feature-rich natural environments, the…

• Synthetic Deformable Tubular Benchmark: A mechanically annotated dataset for evaluating deformable 3D reconstruction
  Íñigo Cirauqui-Viloria · arXiv · Oct 26, 2026

  Evaluating deformable 3D reconstruction requires ground truth linking camera motion, surface deformation, material correspondence and image appearance. We introduce the Synthetic Deformable Tubular Benchmark, generated with LumenMorph, an o…

• Generative Structure from Motion with Native 3D Diffusion
  Haobin Duan, Binbin Huang, Mochu Xiang, Yiqun Zhao et al. · arXiv · Oct 26, 2026

  Recovering an object's 3D structure and camera motion from a few uncalibrated views is a fundamental problem in computer vision. Classical structure from motion methods recover 3D geometry consistent with the input images but cannot recover…