This paper proposes ReChannel, a method for dense prediction using a pretrained DiT model, which keeps the encoder but removes the decoder and adapts it with task LoRA. ReChannel maps each token to it…

The paper introduces PIXIE, a zero-shot framework for estimating 6D pose of an object from an RGB image using only an untextured 3D model.

This paper proposes using color statistics, specifically through novel color transformations, to detect AI-generated synthetic images by exploiting the color-imitation weaknesses of current generative…

The paper introduces GPIC, a massive, permissively licensed, and safety-filtered image corpus of 28 trillion pixels, designed to serve as a stable and accessible benchmark for large-scale visual gener…

This paper analyzes existing watermarking schemes for autoregressive image generators and demonstrates that they are vulnerable to various removal and forgery attacks, suggesting they are unreliable f…

A new framework, CRWKV, is proposed for underwater image enhancement using a Clustering-aware Semantic Dynamic Reordering and Dark-response Modulated Local Propagation methods.

This paper proposes methods for intrinsic decomposition of radiance fields using Gaussian splatting, enabling adaptive modeling, disentanglement, and editing of textures in images.

The paper introduces a method using a U-Net CNN to acquire and estimate detailed sub-surface scattering properties by learning the pixel footprint response, enabling high-resolution relighting of obje…

Places in the Wild introduces a massive, high-resolution RAW photograph dataset of 67,574 images captured in situ across 810 locations, providing unprecedented detail for ecologically valid vision res…

STaR-KV introduces a novel, training-free KV cache compression framework that adaptively re-weights token importance across spatial, temporal, and distributional axes, significantly reducing GPU memor…

This paper proposes a synthetic data generation framework to address the scarcity of real-world industrial defect images for training deep learning models in rotogravure printing quality control. The…

The paper introduces SynCity 3000, a framework for generating large, coherent 3D scenes using a convolutional generator, addressing the scarcity of 3D scene data for training.

GeM-NR proposes a novel, training-free framework to achieve general multi-view image editing, enabling consistent edits that drastically change both the geometry and appearance of a nonrigid scene.

The paper introduces LL-Bench, a comprehensive benchmark for evaluating large-scale generative models on low-level vision tasks, and proposes LL-Score, an MLLM-based evaluator that better aligns quali…

The paper proposes an end-to-end forensic pipeline using steganographic attribution and multimodal harm detection to reliably trace and attribute harmful misuse of AI-generated imagery on social platf…

Rel-Zero proposes a novel zero-watermarking technique that embeds invisible watermarks by exploiting the invariance of relational distances between image patches during AI editing, achieving superior…

QuReC is a unified framework for all-in-one image restoration using a Degradation-Guided Query Reconstruction Module and a Local-Global Response Calibration Module.

The paper proposes RPCASSM, a novel state space model leveraging Robust PCA (RPCA) to accurately detect and segment infrared small targets by separately modeling background and target information base…