16 papers
After a Decade: Bringing Shadow Removal into the Real World with Agentic Training Data
Shilin Hu, Jingyi Xu, Dimitris Samaras +1
Shadow removal looks nearly solved on established benchmarks, yet remains brittle in the real world. Models have advanced; the paired training data they rely on have barely changed…
Domain-Grounded Candidate Selection for Agentic Image Editing: A Shadow Removal Case
Shilin Hu, Jingyi Xu, Dimitris Samaras +1
Commercial vision-language models are reshaping computer vision, with visual priors broad enough to rival task-specific systems. This raises a natural question: do they reduce the…
OmniGF: A Dual-Branch Vision-Language Framework for Unified Gaze Following
Qiaomu Miao, Haoyu Wu, Jingyi Xu +2
Understanding human gaze behavior is essential for complex scene comprehension and human-computer interaction. Traditional gaze following models are typically restricted to pure sp…
Automated Counting of Stacked Objects in Industrial Inspection
Corentin Dumery, Noa Etté, Aoxiang Fan +4
Visual object counting is a fundamental computer vision task in industrial inspection, where accurate, high-throughput inventory tracking and quality assurance are critical. Moreov…
LoRIF: Low-Rank Influence Functions for Scalable Training Data Attribution
Shuangqi Li, Hieu Le, Jingyi Xu +1
Training data attribution (TDA) identifies which training examples most influenced a model's prediction. Influence function methods are a theoretically grounded family of TDA metho…
Personalized Image Descriptions from Attention Sequences
Ruoyu Xue, Hieu Le, Jingyi Xu +5
People can view the same image differently: they focus on different regions, objects, and details in varying orders and describe them in distinct linguistic styles. This leads to s…
Cast and Attached Shadow Detection via Iterative Light and Geometry Reasoning
Shilin Hu, Jingyi Xu, Sagnik Das +2
Shadows encode rich information about scene geometry and illumination, yet existing methods either predict a unified shadow mask or overlook attached shadows entirely. We address t…
Embedding Physical Reasoning into Diffusion-Based Shadow Generation Under the Sun and Sky
Shilin Hu, Jingyi Xu, Akshat Dave +2
Generating realistic cast shadows for inserted foreground objects requires reasoning about scene geometry and illumination. However, most learning-based approaches treat shadow gen…
CORA: Consistency-Guided Semi-Supervised Framework for Reasoning Segmentation
Prantik Howlader, Hoang Nguyen-Canh, Srijan Das +3
Reasoning segmentation seeks pixel-accurate masks for targets referenced by complex, often implicit instructions, requiring context-dependent reasoning over the scene. Recent multi…
Phase-Aligned RoPE for Mixed-Resolution Diffusion Transformer
Haoyu Wu, Jingyi Xu, Qiaomu Miao +2
Rotary positional embeddings (RoPE) are widely used in diffusion transformers (DiTs) to encode spatial relationships, yet their behavior with mixed-resolution tokens remains undere…
Talking Head Generation via AU-Guided Landmark Prediction
Shao-Yu Chang, Jingyi Xu, Hieu Le +1
We propose a two-stage framework for audio-driven talking head generation with fine-grained expression control via facial Action Units (AUs). Unlike prior methods relying on emotio…
Learning to Weight Parameters for Training Data Attribution
Shuangqi Li, Hieu Le, Jingyi Xu +1
We study gradient-based data attribution, aiming to identify which training examples most influence a given output. Existing methods for this task either treat network parameters u…
What is the Right Embedding Space for Contrastive Learning in Referring Expression Counting?
Kostas Triaridis, Panagiotis Kaliosis, E-Ro Nguyen +3
Referring Expression Counting (REC) requires distinguishing visually similar objects described by fine-grained text cues. Existing methods tackle this via image-text contrastive le…
Few-shot Personalized Scanpath Prediction
Ruoyu Xue, Jingyi Xu, Sounak Mondal +4
A personalized model for scanpath prediction provides insights into the visual preferences and attention patterns of individual subjects. However, existing methods for training sca…
Counting Stacked Objects
Corentin Dumery, Noa Etté, Aoxiang Fan +4
Visual object counting is a fundamental computer vision task underpinning numerous real-world applications, from cell counting in biomedicine to traffic and wildlife monitoring. Ho…
All Seeds Are Not Equal: Enhancing Compositional Text-to-Image Generation with Reliable Random Seeds
Shuangqi Li, Hieu Le, Jingyi Xu +1
Text-to-image diffusion models have demonstrated remarkable capability in generating realistic images from arbitrary text prompts. However, they often produce inconsistent results…