Related papers: SPATIALALIGN: Aligning Dynamic Spatial Relationshi…
Recent video foundation models demonstrate impressive visual synthesis but frequently suffer from geometric inconsistencies. While existing methods attempt to inject 3D priors via architectural modifications, they often incur high…
Recent advancements in image-to-video (I2V) generation have shown promising performance in conventional scenarios. However, these methods still encounter significant challenges when dealing with complex scenes that require a deep…
Advances in video generation have significantly improved the realism and quality of created scenes. This has fueled interest in developing intuitive tools that let users leverage video generation as world simulators. Text-to-video (T2V)…
Subject-driven text-to-image (T2I) generation aims to produce images that align with a given textual description, while preserving the visual identity from a referenced subject image. Despite its broad downstream applicability - ranging…
As Text-to-Video (T2V) generation models continue to evolve, the complexity of video evaluation necessitates a fine-grained assessment across various axes. To address this, recent works have focused on developing Multidimensional Video…
Video Super-Resolution (VSR) aims to recover sequences of high-resolution (HR) frames from low-resolution (LR) frames. Previous methods mainly utilize temporally adjacent frames to assist the reconstruction of target frames. However, in the…
Text-to-motion generation, which synthesizes 3D human motions from text inputs, holds immense potential for applications in gaming, film, and robotics. Recently, diffusion-based methods have been shown to generate more diversity and…
Text-to-video (T2V) generation technology holds potential to transform multiple domains such as education, marketing, entertainment, and assistive technologies for individuals with visual or reading comprehension challenges, by creating…
Score Distillation Sampling (SDS) enables high-quality text-to-3D generation by supervising 3D models through the denoising of multi-view 2D renderings, using a pretrained text-to-image diffusion model to align with the input prompt and…
The explosion of visual content available online underscores the requirement for an accurate machine assessor to robustly evaluate scores across diverse types of visual contents. While recent studies have demonstrated the exceptional…
This paper shows that text-only Language Models (LM) can learn to ground spatial relations like "left of" or "below" if they are provided with explicit location information of objects and they are properly trained to leverage those…
In this work we study Weakly Supervised Spatio-Temporal Video Grounding (WSTVG), a challenging task of localizing subjects spatio-temporally in videos using only textual queries and no bounding box supervision. Inspired by recent advances…
Omnidirectional videos (ODVs) provide an immersive visual experience by capturing the 360{\deg} scene. With the rapid advancements in virtual/augmented reality, metaverse, and generative artificial intelligence, the demand for high-quality…
Recent studies have demonstrated the effectiveness of directly aligning diffusion models with human preferences using differentiable reward. However, they exhibit two primary challenges: (1) they rely on multistep denoising with gradient…
Text-to-image (T2I) models are widespread, but their limited safety guardrails expose end users to harmful content and potentially allow for model misuse. Current safety measures are typically limited to text-based filtering or concept…
Image Super-Resolution (SR) aims to reconstruct high-resolution images from degraded low-resolution inputs. While diffusion-based SR methods offer powerful generative capabilities, their performance heavily depends on how semantic priors…
While Multimodal Large Language Models (MLLMs) excel in semantic tasks, they frequently lack the "spatial sense" essential for sophisticated geometric reasoning. Current models typically suffer from exorbitant modality-alignment costs and…
In this paper, we tackle the problem of video alignment, the process of matching the frames of a pair of videos containing similar actions. The main challenge in video alignment is that accurate correspondence should be established despite…
Distinguishing spatial relations is a basic part of human cognition which requires fine-grained perception on cross-instance. Although benchmarks like MME, MMBench and SEED comprehensively have evaluated various capabilities which already…
Diffusion model (DM) based Video Super-Resolution (VSR) approaches achieve impressive perceptual quality. However, they suffer from error accumulation, spatial artifacts, and a trade-off between perceptual quality and fidelity, primarily…