14 papers
PixelSR: Efficient Screen Content Super-Resolution via Pixel Classification
Zhiheng Li, Lei Chen, Jie Zhou +1
Screen content images are generally composed of texts and graphics. Compared to natural images, these man-made images contain a large quantity of sharp but repetitive structures. H…
DisDop: Distillation with Domain Priors for Open-Vocabulary Aerial Object Detection
Ruihao Xu, Yong Liu, Yansong Tang +6
With the widespread application of drones in recent years, object detection of aerial images has attracted increasing attention, especially open-vocabulary aerial detection which i…
CLAP: Contrastive Latent Action Pretraining for Learning Vision-Language-Action Models from Human Videos
Chubin Zhang, Jianan Wang, Zifeng Gao +5
Generalist Vision-Language-Action models remain constrained by the scarcity of robotic data relative to the abundance of human video demonstrations. Existing Latent Action Models a…
Pseudo Depth Meets Gaussian: A Feed-forward RGB SLAM Baseline
Linqing Zhao, Xiuwei Xu, Yirui Wang +5
Incrementally recovering real-sized 3D geometry from a pose-free RGB stream is a challenging task in 3D reconstruction, requiring minimal assumptions on input data. Existing method…
InstaRevive: One-Step Image Enhancement via Dynamic Score Matching
Yixuan Zhu, Haolin Wang, Ao Li +6
Image enhancement finds wide-ranging applications in real-world scenarios due to complex environments and the inherent limitations of imaging devices. Recent diffusion-based method…
GaussianToken: An Effective Image Tokenizer with 2D Gaussian Splatting
Jiajun Dong, Chengkun Wang, Wenzhao Zheng +3
Effective image tokenization is crucial for both multi-modal understanding and generation tasks due to the necessity of the alignment with discrete text data. To this end, existing…
GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation
Chubin Zhang, Hongliang Song, Yi Wei +3
In this work, we introduce the Geometry-Aware Large Reconstruction Model (GeoLRM), an approach which can predict high-quality assets with 512k Gaussians and 21 input images in only…
Narrative Action Evaluation with Prompt-Guided Multimodal Interaction
Shiyi Zhang, Sule Bai, Guangyi Chen +4
In this paper, we investigate a new problem called narrative action evaluation (NAE). NAE aims to generate professional commentary that evaluates the execution of an action. Unlike…
DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery
Yixuan Zhu, Ao Li, Yansong Tang +3
The recovery of occluded human meshes presents challenges for current methods due to the difficulty in extracting effective image features under severe occlusion. In this paper, we…
Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression
Hancheng Ye, Chong Yu, Peng Ye +5
Recent Vision Transformer Compression (VTC) works mainly follow a two-stage scheme, where the importance score of each model unit is first evaluated or preset in each submodule, fo…
MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer
Jianjian Cao, Peng Ye, Shengze Li +4
Vision-Language Transformers (VLTs) have shown great success recently, but are meanwhile accompanied by heavy computation costs, where a major reason can be attributed to the large…
Learning Dual-Level Deformable Implicit Representation for Real-World Scale Arbitrary Super-Resolution
Zhiheng Li, Muheng Li, Jixuan Fan +4
Scale arbitrary super-resolution based on implicit image function gains increasing popularity since it can better represent the visual world in a continuous manner. However, existi…
Segment and Caption Anything
Xiaoke Huang, Jianfeng Wang, Yansong Tang +5
We propose a method to efficiently equip the Segment Anything Model (SAM) with the ability to generate regional captions. SAM presents strong generalizability to segment anything w…
Skip-Plan: Procedure Planning in Instructional Videos via Condensed Action Space Learning
Zhiheng Li, Wenjia Geng, Muheng Li +4
In this paper, we propose Skip-Plan, a condensed action space learning method for procedure planning in instructional videos. Current procedure planning methods all stick to the st…