Search Results for author:
Found 16 papers, 1 papers with code
Top-Down Compression: Revisit Efficient Vision Token Projection for Visual Instruction Tuning
Visual instruction tuning aims to enable large language models to comprehend the visual world, with a pivotal challenge lying in establishing an effective vision-to-language projection.
CamPoint: Boosting Point Cloud Segmentation with Virtual Camera
Local features aggregation and global information perception are the fundamental to point cloud segmentation.
CoSER: Towards Consistent Dense Multiview Text-to-Image Generator for 3D Creation
To further enhance cross-view consistency and alleviate content drift, CoSER rapidly scan all views in spiral bidirectional manner to aware holistic information and then scores each point based on semantic material.
LokiTalk: Learning Fine-Grained and Generalizable Correspondences to Enhance NeRF-based Talking Head Synthesis
Despite significant progress in talking head synthesis since the introduction of Neural Radiance Fields (NeRF), visual artifacts and high training costs persist as major obstacles to large-scale commercial adoption.
DR-BFR: Degradation Representation with Diffusion Models for Blind Face Restoration
DR-BFR comprises two modules: 1) Degradation Representation Module (DRM): This module extracts degradation representation with content-irrelevant features from LQ faces and estimates a reasonable distribution in the degradation space through contrastive learning and a specially designed LQ reconstruction.
Focus on Neighbors and Know the Whole: Towards Consistent Dense Multiview Text-to-Image Generator for 3D Creation
To further enhance cross-view consistency and alleviate content drift, CoSER rapidly scan all views in spiral bidirectional manner to aware holistic information and then scores each point based on semantic material.
Blaze3DM: Marry Triplane Representation with Diffusion for 3D Medical Inverse Problem Solving
Solving 3D medical inverse problems such as image restoration and reconstruction is crucial in modern medical field.
BlazeBVD: Make Scale-Time Equalization Great Again for Blind Video Deflickering
Developing blind video deflickering (BVD) algorithms to enhance video temporal consistency, is gaining importance amid the flourish of image processing and video generation.
Learning Dynamic Tetrahedra for High-Quality Talking Head Synthesis
Recent works in implicit representations, such as Neural Radiance Fields (NeRF), have advanced the generation of realistic and animatable head avatars from video sequences.
General Method for Solving Four Types of SAT Problems
We experimentally verify that this paradigm can prune the unnecessary search space to find the optimal Boolean assignments for the problem.
DiffBFR: Bootstrapping Diffusion Model Towards Blind Face Restoration
This design is implemented with two key components: 1) Identity Restoration Module (IRM) for preserving the face details in results.
StyO: Stylize Your Face in Only One-shot
And it introduces a novel triple reconstruction loss to fine-tune the pre-trained LDM for encoding style and content into corresponding identifiers; 2) Fine-grained Content Controller (FCC) for the recombination phase.
DropKey for Vision Transformer
Given exploration on the above three questions, we present the novel DropKey method that regards Key as the drop unit and exploits decreasing schedule for drop ratio, improving ViTs in a general way.
Masked Reconstruction Contrastive Learning with Information Bottleneck Principle
In order to alleviate the discriminative information overfitting problem effectively, we employ the reconstruction task to regularize the discriminative task.
Ranked #22 on
Self-Supervised Image Classification
on ImageNet
DropKey
Given exploration on the above three questions, we present the novel DropKey method that regards Key as the drop unit and exploits decreasing schedule for drop ratio, improving ViTs in a general way.
DFS: A Diverse Feature Synthesis Model for Generalized Zero-Shot Learning
In this paper, we propose to enhance the generalizability of GZSL models via improving feature diversity of unseen classes.
