相关论文: Genuine Knowledge from Practice: Diffusion Test-Ti…
Recent work indicates that video recognition models are vulnerable to adversarial examples, posing a serious security risk to downstream applications. However, current research has primarily focused on adversarial attacks, with limited work…
As a common natural weather condition, rain can obscure video frames and thus affect the performance of the visual system, so video derain receives a lot of attention. In natural environments, rain has a wide variety of streak types, which…
Adverse weather severely impairs real-world visual perception, while existing vision models trained on synthetic data with fixed parameters struggle to generalize to complex degradations. To address this, we first construct HFLS-Weather, a…
Thermal infrared imaging exhibits considerable potentials for robotic perception tasks, especially in environments with poor visibility or challenging lighting conditions. However, TIR images typically suffer from heavy non-uniform…
Diffusion models have achieved remarkable success in the domain of text-guided image generation and, more recently, in text-guided image editing. A commonly adopted strategy for editing real images involves inverting the diffusion process…
Text-to-image diffusion models rely on text embeddings from a pre-trained text encoder, but these embeddings remain fixed across all diffusion timesteps, limiting their adaptability to the generative process. We propose Diffusion Adaptive…
Since distribution shifts are likely to occur after a model's deployment and can drastically decrease the model's performance, online test-time adaptation (TTA) continues to update the model during test-time, leveraging the current test…
Extreme precipitation causes severe societal and economic damage, and weather control has long been discussed as a potential mitigation strategy. However, to the best of our knowledge, perturbation-based interventions for weather control…
Wearable human activity recognition (WHAR) models often suffer from performance degradation under real-world cross-user distribution shifts. Test-time adaptation (TTA) mitigates this degradation by adapting models online using unlabeled…
Dexterous telemanipulation critically relies on the continuous and stable tracking of the human operator's commands to ensure robust operation. Vison-based tracking methods are widely used but have low stability due to anomalies such as…
Accident anticipation is essential for proactive and safe autonomous driving, where even a brief advance warning can enable critical evasive actions. However, two key challenges hinder real-world deployment: (1) noisy or degraded sensory…
Video try-on stands as a promising area for its tremendous real-world potential. Prior works are limited to transferring product clothing images onto person videos with simple poses and backgrounds, while underperforming on casually…
We present a motion-adaptive temporal attention mechanism for parameter-efficient video generation built upon frozen Stable Diffusion models. Rather than treating all video content uniformly, our method dynamically adjusts temporal…
Video virtual try-on aims to generate realistic sequences that maintain garment identity and adapt to a person's pose and body shape in source videos. Traditional image-based methods, relying on warping and blending, struggle with complex…
Recent advancements in adverse weather restoration have shown potential, yet the unpredictable and varied combinations of weather degradations in the real world pose significant challenges. Previous methods typically struggle with…
Test-Time Adaptation (TTA) enables real-time adaptation to domain shifts without off-line retraining. Recent TTA methods have predominantly explored additive approaches that introduce lightweight modules for feature refinement. Recently, a…
Video inverse problems are fundamental to streaming, telepresence, and AR/VR, where high perceptual quality must coexist with tight latency constraints. Diffusion-based priors currently deliver state-of-the-art reconstructions, but existing…
Diffusion models have emerged as a key pillar of foundation models in visual domains. One of their critical applications is to universally solve different downstream inverse tasks via a single diffusion prior without re-training for each…
The zero-shot capabilities of Vision-Language Models (VLMs) have been widely leveraged to improve predictive performance. However, previous works on transductive or test-time adaptation (TTA) often make strong assumptions about the data…
In recent years, the rapid expansion of dataset sizes and the increasing complexity of deep learning models have significantly escalated the demand for computational resources, both for data storage and model training. Dataset distillation…