activity
20202025
most citedUDC 2020 Challenge on Image Restoration of Under-Display Camera: Methods and Results

5 citations · 5 across the 4 of their papers we have counts for

collaborators
Showing cs.CVShow all

9 papers · 1 filter

cs.CV2025

Low-Bitrate Video Compression through Semantic-Conditioned Diffusion

Lingdong Wang, Guan-Ming Su, Divya Kothandaraman +3

Traditional video codecs optimized for pixel fidelity collapse at ultra-low bitrates and produce severe artifacts. This failure arises from a fundamental misalignment between pixel…

cs.CV2025

Zero-Shot Personalized Camera Motion Control for Image-to-Video Synthesis

Pooja Guhan, Divya Kothandaraman, Geonsun Lee +3

Specifying nuanced and compelling camera motion remains a significant hurdle for non-expert creators using generative tools, creating an "expressive gap" where generic text prompts…

cs.CV2025

Scene-Action Prompt Fusion for Coherent Text-to-Video Storytelling

Taewon Kang, Divya Kothandaraman, Ming C. Lin

Generating coherent long-form video sequences from discrete text prompts remains challenging due to difficulties in maintaining temporal coherence, semantic consistency, and scene-…

cs.CV2024

ImPoster: Text and Frequency Guidance for Subject Driven Action Personalization using Diffusion Models

Divya Kothandaraman, Kuldeep Kulkarni, Sumit Shekhar +2

We present ImPoster, a novel algorithm for generating a target image of a 'source' subject performing a 'driving' action. The inputs to our algorithm are a single pair of a source…

cs.CV2024

3D-free meets 3D priors: Novel View Synthesis from a Single Image with Pretrained Diffusion Guidance

Taewon Kang, Divya Kothandaraman, Dinesh Manocha +1

Recent 3D novel view synthesis (NVS) methods often require extensive 3D data for training, and also typically lack generalization beyond the training distribution. Moreover, they t…

cs.CV2024

Text Prompting for Multi-Concept Video Customization by Autoregressive Generation

Divya Kothandaraman, Kihyuk Sohn, Ruben Villegas +3

We present a method for multi-concept customization of pretrained text-to-video (T2V) models. Intuitively, the multi-concept customized video can be derived from the (non-linear) i…