The paper introduces ZipDepth, a compact monocular depth network that achieves high zero-shot accuracy with low computational demands by combining an efficient encoder-decoder and large-scale knowledg…

The paper proposes VLM3, a simple, scalable method that demonstrates standard Vision Language Models (VLMs) can natively learn 3D understanding by focusing on architectural simplicity and specific dat…

The paper proposes xModel-KD, a cross-modal knowledge distillation framework, to improve 3D point cloud segmentation by effectively transferring rich appearance cues from 2D images to sparse 3D geomet…

The paper introduces a Mixture-Density Representation (MDA) to model depth ambiguity, effectively eliminating 'flying-point' artifacts at object boundaries by allowing pixels to predict multiple possi…

VISUALTHINK-VLA introduces a visual intermediate-reasoning framework that guides action prediction using compact visual evidence, achieving high accuracy and significantly low latency for real-time Vi…

The paper presents SenseNova-Vision, a unified multimodal model for computer vision tasks using natural language instructions and optional visual prompts, trained primarily on a new corpus and requiri…

The paper introduces Multi-temporal Referring Segmentation (MTRS), a new task requiring models to segment language-described temporal changes, and proposes MTRefSeg-R1, a specialized framework that ac…

This paper proposes HDR (Hierarchical Denoising for Visual Reasoning), a framework that integrates hierarchical latents into causal video generation for multi-step reasoning, enabling coarse-to-fine r…

The paper introduces PAR3D, a unified part-aware 3D-MLLM framework, to enhance 3D scene understanding by enabling models to reason about and ground both whole objects and their fine-grained parts.

RayDer introduces a unified, feed-forward transformer that simplifies self-supervised novel view synthesis (NVS) by consolidating camera estimation, scene reconstruction, and rendering into a single,…

The paper introduces VLM-IE3D, a framework that enhances 2D vision-language models with implicit and explicit 3D geometries learned from RGB videos, achieving superior performance on various 3D tasks.

The paper proposes a Transformer-based end-to-end architecture to reconstruct 3D house roof wireframes from sparse point clouds and semantic data, achieving state-of-the-art results on the S23DR Chall…

The paper proposes a real-time, predictive, and task-aware foveated imaging system that dynamically allocates limited sensor bandwidth to task-relevant regions of interest, significantly improving per…

The paper proposes Locality-Aware Redundancy Pruning (LoRP), a training-free method that prunes LLM layers by exploiting localized inter-layer redundancy, leading to improved efficiency while maintain…

The paper proposes GASP, a framework that injects fundamental geometric priors directly into Vision-Language Models (VLMs) using ground-truth video geometry, significantly enhancing 3D spatial reasoni…