Search Results

This paper introduces an effective method for computation-efficient personalized style video generation without requiring access to any personalized video data. It reduces the necessary generation time of similarly sized video diffusion models from 25 ...

Denoising diffusion models have emerged as a dominant approach for image generation, however they still suffer from slow convergence in training and color shift issues in sampling. In this paper, we identify that these obstacles can be largely ...$$

In this study, we delve into the generation of high-resolution images from pre-trained diffusion models, addressing persistent challenges, such as repetitive patterns and structural distortions, that emerge when models are applied beyond their ...

Although video generation has made great progress in capacity and controllability and is gaining increasing attention, currently available video generation models still make minimal progress in the video length they can generate. Due to the lack ...$\mathrm{}\mathrm{}$

Optimizing a text-to-image diffusion model with a given reward function is an important but underexplored research area. In this study, we propose Deep Reward Tuning (DRTune), an algorithm that directly supervises the final output image of a text-...

Recent advances in event-based vision suggest that they complement traditional cameras by providing continuous observation without frame rate limitations and high dynamic range which are well-suited for correspondence tasks such as optical flow ...

This paper proposes a simple, yet effective framework, called GiT, simultaneously applicable for various vision tasks only with a vanilla ViT. Motivated by the universality of the Multi-layer Transformer architecture (e.g., GPT) widely used in ...

We present [inline-graphic not available: see fulltext] , a versatile multi-modal large language model (MLLM) with a joint mixing of model weights, visual embeddings and image scales. First, for stronger vision-language alignment, we unfreeze the ...

Understanding and modeling the popularity of User Generated Content (UGC) short videos on social media platforms presents a critical challenge with broad implications for content creators and recommendation systems. This study delves deep into the ...

Neuromorphic sensors, specifically event cameras, revolutionize visual data acquisition by capturing pixel intensity changes with exceptional dynamic range, minimal latency, and energy efficiency, setting them apart from conventional frame-based ...

Existing benchmarks for 3D semantic occupancy prediction in autonomous driving are limited by low resolution (up to $[512\times 512\times 40]$ with 0.2 m voxel size) and inaccurate annotations, hindering the unification of 3D scene understanding through the ...$\mathrm{}$$\mathrm{}\mathrm{}\mathrm{}$

The remarkable progress of Multi-modal Large Language Models (MLLMs) has gained unparalleled attention. However, their capabilities in visual math problem-solving remain insufficiently evaluated and understood. We investigate current benchmarks to ...

Large foundation models have recently emerged as a prominent focus of interest, attaining superior performance in widespread scenarios. Due to the scarcity of 3D data, many efforts have been made to adapt pre-trained transformers from vision to 3D ...

In this paper, we investigate how to conduct transfer learning to adapt Stable Diffusion to downstream visual dense prediction tasks such as semantic segmentation and depth estimation. We focus on fine-tuning the Stable Diffusion model, which has ...

We introduce a new method for learning a generative model of articulated 3D animal motions from raw, unlabeled online videos. Unlike existing approaches for 3D motion synthesis, our model requires no pose annotations or parametric shape models for ...

Video outpainting is a challenging task, aiming at generating video content outside the viewport of the input video while maintaining inter-frame and intra-frame consistency. Existing methods fall short in either generation quality or flexibility. ...

One-to-one matching is a crucial design in DETR-like object detection frameworks. It enables the DETR to perform end-to-end detection. However, it also faces challenges of lacking positive sample supervision and slow convergence speed. Several recent ...

Large Language Models (LLMs) have become pivotal in advancing the field of artificial intelligence, yet their immense sizes pose significant challenges for both fine-tuning and deployment. Current post-training pruning methods, while reducing the sizes ...

We propose SPHINX-X, an extensive Multimodality Large Language Model (MLLM) series developed upon SPHINX. To improve the architecture and training efficiency, we modify the SPHINX framework by removing redundant visual encoders, bypassing fully-padded ...

We introduce Motion-I2V, a novel framework for consistent and controllable text-guided image-to-video generation (I2V). In contrast to previous methods that directly learn the complicated image-to-video mapping, Motion-I2V factorizes I2V into two stages ...