2026-07-07

19 papers from arXiv

← Back to history

SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion

Paul Engstler, Iro Laina, Christian Rupprecht, Andrea Vedaldi

We present SynCity 3000, a framework for generating 3D scenes that are globally coherent while enabling fine-grained layout control. Building on the ability of current image-to-3D generators to produce complex 3D assets from a single image, we extend this capability to the scale of entire scenes by adapting the generator to be applicable as a convolutional operator. We achieve this by fine-tuning ...

cs.CVPR

Deform360: A Massive Multi-view Visuotactile Dataset for Deformable World Models

Hongyu Li, Wanjia Fu, Xiaoyan Cong, Zekun Li, Binghao Huang et al.

Predicting object dynamics (i.e., world modeling) is a fundamental challenge for robotic manipulation, and modeling deformable objects presents a particularly difficult case due to their high-dimensional state spaces and complex material properties. While current world models approach this through two distinct paradigms: learning the dynamics over the 2D pixel space or more explicit 3D geometric s...

cs.ROcs.CVECCV

InFlux++: Real and Synthetic Data for Estimating Dynamic Camera Intrinsics

Erich Liang, Caleb Kha-Uong, Chinmaya Saran, Sreemanti Dey, David W. Liu et al.

Camera intrinsics are vital for recovering 3D structure from 2D video. However, most 3D algorithms assume fixed intrinsics throughout a video, an assumption that often fails for real-world in-the-wild videos. Consequently, estimating per-frame intrinsics from RGB images is critical for making 3D methods robust to videos with dynamic intrinsics. InFlux previously advanced this research direction by...

cs.CVECCV

MV-Forcing: Long Multi-View Video Generation via 4D-Grounded Spatio-Temporal Self-Forcing

Gal Fiebelman, Hadar Averbuch-Elor, Sagie Benaim

Recent advances in video diffusion models have enabled either long single-view generation through temporal autoregression, or short multi-view synthesis through bidirectional attention. However, generating long, multi-view consistent videos of dynamic scenes remains unsolved. In this work, we present MV-Forcing, a framework that composes temporal and view-wise autoregression within a single diffus...

cs.CVcs.GRECCV

PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space

Sensen Gao, Zhaoqing Wang, Qihang Cao, Dongdong Yu, Changhu Wang et al.

3D reconstruction and generation are commonly tackled by separate paradigms: pixel-based regression for reconstruction, and latent diffusion for generation. Recent works attempt to unify them in latent space, but with notable drawbacks: the diffusion objective is defined on latent features rather than the underlying 3D representation, and both branches suffer from information loss introduced by la...

cs.CVPR

ReCal3R: Reliability-Calibrated Learning Rates for Streaming 3D Reconstruction

Xinze Li, Yiyuan Wang, Pengxu Chen, Wentao Fan, Weifeng Su et al.

Streaming 3D reconstruction relies on a compact recurrent scene state to process long image streams in linear time and bounded memory. However, repeated updates can gradually corrupt this state, causing reliable historical information to be overwritten by noisy or ambiguous observations. We introduce ReCal3R, a reliability-calibrated learning rate method for recurrent 3D reconstruction. Instead of...

cs.CVPR

Geometric Reciprocity: Unlocking Self-Supervision for Stereoscopic Video Generation

Jingyi Lu, Kai Han

Monocular-to-stereo conversion synthesizes stereoscopic content from 2D videos for immersive 3D experiences. In modern Depth-Image-Based Rendering (DIBR) approaches, stereo inpainting of disocclusions is the critical bottleneck. Training-based methods achieve superior quality but rely on scarce stereo pairs or synthetic data with domain gaps. We address this through the first self-supervised frame...

cs.CVICML

Beyond Isolated Objects: Relationship-aware Open Vocabulary Scene Understanding via 3D Scene Graph Analysis

Xianhao Chen, Jiarui Hu, Yuanbo Yang, Xiyu Zhang, Tengyue Wang et al.

Open-vocabulary 3D scene understanding aims to segment 3D scenes beyond predefined categories by transferring semantic knowledge from vision-language models. Existing methods have advanced this task by lifting language-aligned 2D features into 3D, yet they often rely on context-independent semantic representations, leaving object relationships underexplored for contextual refinement. We propose Re...

cs.CVcs.ROPR

WildSplat: Feedforward Gaussian Splatting from Unposed In-the-Wild Images

Xiyu Zhang, Jingyu Zhuang, Hongjia Zhai, Zizheng Yan, Jinwei Chen et al.

While feedforward 3D reconstruction excels at efficient novel view synthesis, it typically falters when faced with scenes under varying illumination. To this end, we introduce WildSplat, the first feedforward 3D Gaussian Splatting framework capable of appearance-conditioned novel-view synthesis for unposed in-the-wild images. To handle inconsistent photometric conditions, we propose a dual-branch ...

cs.CVECCV

Topological Shape Representation for Aneurysm -- Bifurcation Detection

Akshay Gokhale, Mansi Dhamne

Automated detection of intracranial aneurysms (IAs) from CT angiography (CTA) is severely hindered by high false-positive rates. Convolutional neural networks (CNNs) rely on local pixel intensities, causing systematic confusion between saccular aneurysms and vascular bifurcations -- a problem especially acute for small lesions (<3 mm), where detection sensitivity falls below 60%. We propose a plug...

cs.CVcs.AIcs.LGPR

GUSH3R: Everyone Everywhere All at Once as Gaussians

Keito Abe, Kaede Shiohara, Takashi Otonari, Toshihiko Yamasaki

Reconstructing dynamic human-scene environments from monocular videos is a challenging problem that requires jointly modeling scene geometry, camera motion, and non-rigid human dynamics while enabling photorealistic rendering. Recent feed-forward methods can efficiently predict geometry, but they are often limited to non-photorealistic representations such as point clouds and meshes, or they fail ...

cs.CVPR

Cortex: A Bidirectionally Aligned Embodied Agent Framework for Long-horizon Manipulation

Jiaqi Peng, Xiqian Yu, Delin Feng, Yuqiang Yang, Wenzhe Cai et al.

While recent Vision-Language-Action (VLA) models show promise toward generalist manipulation policies, they struggle with long-horizon tasks due to their Markovian nature-relying solely on current observations. Hierarchical dual-system methods address this but suffer from a gap between high-level planning semantics and low-level execution kinematics. We introduce Cortex, a bidirectionally aligned ...

cs.ROcs.AIcs.CVPR

Learning Probabilistic Embeddings for Unsupervised Action Segmentation

Shuai Li, Duc Manh Vu, Juergen Gall

This paper concerns the problem of unsupervised temporal action segmentation for long, untrimmed videos. Recent successful approaches follow a joint representation learning and clustering paradigm, where optimal transport (OT) is adopted to produce pseudo labels for learning frame representations. These approaches alternate between estimating pseudo labels using OT and optimizing the parameters wi...

cs.CVECCV

Repurposing CLIP to Localize at Pixel Level

Jiaxiang Fang, Shiqiang Ma, Jing Wang, Siyu Chen, Fei Guo et al.

Large-scale Vision-Language Models like CLIP have demonstrated impressive open-set localization capabilities at the image level. However, adapting this capability to pixel-level dense prediction poses challenges due to global feature biases. In this paper, we introduce CLIPix, a simple yet effective framework that repurposes CLIP to perform pixel-level localization. By tracing back CLIP's classifi...

cs.CVTMM

Open Problems in AI Incident Governance

Harleen Kaur Sidhu, Rebecca Scholefield, Nour Annan, Kevin Hernandez, Isabel Nieh Hou et al.

AI systems may produce failures after deployment that pre-deployment safety assessments do not anticipate. Managing these failures requires what we refer to as adequate \textit{AI incident governance}, where having good definitions, taxonomies, monitoring practices, reporting mechanisms, and incident analysis is essential. We examine existing frameworks related to AI incident governance by regulat...

cs.CYcs.AIICML

Semantic Video Communication via Multi-Scale Convolution and Dynamic Routing for Next-Generation Networks

Gengtian Shi, Jinze Yu, Chenhao Wu, Shaofei Wang, Eiji Fukuzawa et al.

The exponential growth of video traffic demands novel semantic communication paradigms that transmit meaning rather than raw bits. We present a generative AI-enabled framework for semantic video communication addressing two critical challenges: efficient hierarchical temporal modeling for bandwidth-constrained transmission and robust semantic alignment between video content and natural language qu...

cs.CVAAAI

RADIANCE: Relative Adaptive Denoising with IP-Adapter for Novel Concept Enhancement

Zi-Xiang Ni, Bo-Lun Huang, Teng-Fang Hsiao, Bo-Kai Ruan, Hong-Han Shuai

Text-to-image (T2I) diffusion models have achieved striking progress but still struggle to synthesize rare concepts involving unusual attribute-object pairings, often resulting in concept omission or semantic drift where a dominant entity overwhelms the generation. Tracing these failures to a lack of compositional balance during the denoising trajectory, we propose RADIANCE, a training-free framew...

cs.CVECCV

LangLoc: "Tell Me What You See"

Shaurya Kishore Panwar, Roham Zendehdel Nobari, Shirley Feng Yi Lau, Abu Bakr Rahman Shaik, Manuel Günther et al.

We tackle fine-grained indoor localization from natural language: given a free-form description of one's surroundings, estimate the observer's 2D position and heading within a known 3D environment. Language queries are lightweight, privacy-preserving, and need no camera - yet prior work stops at coarse scene retrieval and cannot resolve an intra-scene pose. We close this gap with LangLoc, a three-...

cs.CVECCV

MemPose: Category-level Object Pose Estimation with Memory

Xiao Lin, Minghao Zhu, Yun Peng, Liuyi Wang, Qiyi Wang et al.

In the pursuit of robust and generalizable category-level object pose estimation, most existing methods adopt parametric formulations that learn effective representations from data, yet they primarily encode category-level patterns into fixed shape priors or static parameter weights, which limits their scalability to highly diverse instances. In this paper, we rethink category-level pose estimatio...

cs.CVcs.AIECCV