Related papers: HAVIR: HierArchical Vision to Image Reconstruction…
Despite diffusion models having shown powerful abilities to generate photorealistic images, generating videos that are realistic and diverse still remains in its infancy. One of the key reasons is that current methods intertwine spatial…
Hyperspectral image (HSI) restoration aims at recovering clean images from degraded observations and plays a vital role in downstream tasks. Existing model-based methods have limitations in accurately modeling the complex image…
Imagine living in a world composed solely of primitive shapes, could you still recognise familiar objects? Recent studies have shown that abstract images-constructed by primitive shapes-can indeed convey visual semantic information to deep…
Most of the research in content-based image retrieval (CBIR) focus on developing robust feature representations that can effectively retrieve instances from a database of images that are visually similar to a query. However, the retrieved…
Novel view synthesis (NVS) boosts immersive experiences in computer vision and graphics. Existing techniques, though progressed, rely on dense multi-view observations, restricting their application. This work takes on the challenge of…
The enhanced Deep Hierarchical Video Compression-DHVC 2.0-has been introduced. This single-model neural video codec operates across a broad range of bitrates, delivering not only superior compression performance to representative methods…
Story continuation focuses on generating the next image in a narrative sequence so that it remains coherent with both the ongoing text description and the previously observed images. A central challenge in this setting lies in utilizing…
All-in-One Image Restoration (AiOIR) has advanced significantly, offering promising solutions for complex real-world degradations. However, most existing approaches rely heavily on degradation-specific representations, often resulting in…
The success of large-scale contrastive vision-language pretraining (CLIP) has benefited both visual recognition and multimodal content understanding. The concise design brings CLIP the advantage in inference efficiency against other…
Understanding the encoding and decoding mechanisms of dynamic neural responses to different visual stimuli is an important topic in exploring how the brain represents visual information. Currently, hierarchically deep neural networks (DNNs)…
Structuring latent representations in a hierarchical manner enables models to learn patterns at multiple levels of abstraction. However, most prevalent image understanding models focus on visual similarity, and learning visual hierarchies…
Analyzing a visual scene by inferring the configuration of a generative model is widely considered the most flexible and generalizable approach to scene understanding. Yet, one major problem is the computational challenge of the inference…
Text-to-image generation has witnessed significant advancements with the integration of Large Vision-Language Models (LVLMs), yet challenges remain in aligning complex textual descriptions with high-quality, visually coherent images. This…
Recent advancements in video generation have primarily leveraged diffusion models for short-duration content. However, these approaches often fall short in modeling complex narratives and maintaining character consistency over extended…
Deep image restoration models aim to learn a mapping from degraded image space to natural image space. However, they face several critical challenges: removing degradation, generating realistic details, and ensuring pixel-level consistency.…
Image compression under ultra-low bitrates remains challenging for both conventional learned image compression (LIC) and generative vector-quantized (VQ) modeling. Conventional LIC suffers from severe artifacts due to heavy quantization,…
Reconstructing visual stimuli from functional Magnetic Resonance Imaging fMRI enables fine-grained retrieval of brain activity. However, the accurate reconstruction of diverse details, including structure, background, texture, color, and…
Neural networks are widely adopted to solve complex and challenging tasks. Especially in high-stakes decision-making, understanding their reasoning process is crucial, yet proves challenging for modern deep networks. Feature visualization…
This work explores text-to-image retrieval for queries that specify or describe a semantic category. While vision-and-language models (VLMs) like CLIP offer a straightforward open-vocabulary solution, they map text and images to distant…
Reconstructing seeing images from fMRI recordings is an absorbing research area in neuroscience and provides a potential brain-reading technology. The challenge lies in that visual encoding in brain is highly complex and not fully revealed.…