Related papers: Active Sampling for Ultra-Low-Bit-Rate Video Compr…
Transferring large amount of high resolution images over limited bandwidth is an important but very challenging task. Compressing images using extremely low bitrates (<0.1 bpp) has been studied but it often results in low quality images of…
In recent years, diffusion models have demonstrated remarkable success in high-fidelity image synthesis. However, fine-tuning these models for specialized domains, such as medical imaging, remains challenging due to limited domain-specific…
Event cameras excel at high-speed, low-power, and high-dynamic-range scene perception. However, as they fundamentally record only relative intensity changes rather than absolute intensity, the resulting data streams suffer from a…
Event-based video reconstruction has garnered increasing attention due to its advantages, such as high dynamic range and rapid motion capture capabilities. However, current methods often prioritize the extraction of temporal information…
Despite their remarkable performance, modern Diffusion Transformers are hindered by substantial resource requirements during inference, stemming from the fixed and large amount of compute needed for each denoising step. In this work, we…
Continuous video monitoring in surveillance, robotics, and wearable systems faces a fundamental power constraint: conventional RGB cameras consume substantial energy through fixed-rate capture. Event cameras offer sparse, motion-driven…
A diffusion-based voice conversion (VC) model (e.g., VoiceGrad) can achieve high speech quality and speaker similarity; however, its conversion process is slow owing to iterative sampling. FastVoiceGrad overcomes this limitation by…
Long-trajectory video generation is a crucial yet challenging task for world modeling primarily due to the limited scalability of existing video diffusion models (VDMs). Autoregressive models, while offering infinite rollout, suffer from…
Discrete diffusion models are a class of generative models that construct sequences by progressively denoising samples from a categorical noise distribution. Beyond their rapidly growing ability to generate coherent natural language, these…
Recent hybrid video generation models combine autoregressive temporal dynamics with diffusion-based spatial denoising, but their sequential, iterative nature leads to error accumulation and long inference times. In this work, we propose a…
Generating physically plausible human motion is crucial for applications such as character animation and virtual reality. Existing approaches often incorporate a simulator-based motion projection layer to the diffusion process to enforce…
Recent video inpainting methods have achieved encouraging improvements by leveraging optical flow to guide pixel propagation from reference frames either in the image space or feature space. However, they would produce severe artifacts in…
Recent video generation models largely rely on video autoencoders that compress pixel-space videos into latent representations. However, existing video autoencoders suffer from three major limitations: (1) fixed-rate compression that wastes…
Computed Tomography (CT) technology reduces radiation haz-ards to the human body through sparse sampling, but fewer sampling angles pose challenges for image reconstruction. Score-based generative models are widely used in sparse-view CT…
Learned image compression has achieved competitive rate-distortion performance, but very-low-bitrate reconstruction remains difficult because the transmitted representation often cannot preserve fine textures and local structures.…
Diffusion probabilistic models (DPMs) have become a popular approach to conditional generation, due to their promising results and support for cross-modal synthesis. A key desideratum in conditional synthesis is to achieve high…
We propose DAVIS, a Diffusion-based Audio-VIsual Separation framework that solves the audio-visual sound source separation task through generative learning. Existing methods typically frame sound separation as a mask-based regression…
Although diffusion model has shown great potential for generating higher quality images than GANs, slow sampling speed hinders its wide application in practice. Progressive distillation is thus proposed for fast sampling by progressively…
Few-shot image synthesis entails generating diverse and realistic images of novel categories using only a few example images. While multiple recent efforts in this direction have achieved impressive results, the existing approaches are…
Diffusion models are powerful tools for sampling from high-dimensional distributions by progressively transforming pure noise into structured data through a denoising process. When equipped with a guidance mechanism, these models can also…