Related papers: Region in Context: Text-condition Image editing wi…
We introduce a generalized framework for Scene Change Detection (SCD) that addresses the core ambiguity of distinguishing "relevant" from "nuisance" changes, enabling effective joint training of a single model across diverse domains and…
As robots begin to cohabit with humans in semi-structured environments, the need arises to understand instructions involving rich variability---for instance, learning to ground symbols in the physical world. Realistically, this task must…
Many vision-language tasks can be reduced to the problem of sequence prediction for natural language output. In particular, recent advances in image captioning use deep reinforcement learning (RL) to alleviate the "exposure bias" during…
Conditioning image generation on specific features of the desired output is a key ingredient of modern generative models. However, existing approaches lack a general and unified way of representing structural and semantic conditioning at…
Multimodal large language models often struggle with faithful reasoning in complex visual scenes, where intricate entities and relations require precise visual grounding at each step. This reasoning unfaithfulness frequently manifests as…
We present SegGPT, a generalist model for segmenting everything in context. We unify various segmentation tasks into a generalist in-context learning framework that accommodates different kinds of segmentation data by transforming them into…
Image-text matching plays a central role in bridging the semantic gap between vision and language. The key point to achieve precise visual-semantic alignment lies in capturing the fine-grained cross-modal correspondence between image and…
Feature disentanglement of the foreground target objects and the background surrounding context has not been yet fully accomplished. The lack of network interpretability prevents advancing for feature disentanglement and better…
Automatic photo adjustment is to mimic the photo retouching style of professional photographers and automatically adjust photos to the learned style. There have been many attempts to model the tone and the color adjustment globally with…
Representing the semantics of words is a long-standing problem for the natural language processing community. Most methods compute word semantics given their textual context in large corpora. More recently, researchers attempted to…
This paper presents the first study on adapting the visual in-context learning (V-ICL) paradigm to optical character recognition tasks, specifically focusing on text removal and segmentation. Most existing V-ICL generalists employ a…
The compositional structure of language enables humans to decompose complex phrases and map them to novel visual concepts, showcasing flexible intelligence. While several algorithms exhibit compositionality, they fail to elucidate how…
Addressing the limitations of text as a source of accurate layout representation in text-conditional diffusion models, many works incorporate additional signals to condition certain attributes within a generated image. Although successful,…
Matching cross-view images is challenging because the appearance and viewpoints are significantly different. While low-level features based on gradient orientations or filter responses can drastically vary with such changes in viewpoint,…
Bilingual lexicon induction, translating words from the source language to the target language, is a long-standing natural language processing task. Recent endeavors prove that it is promising to employ images as pivot to learn the lexicon…
This paper presents a novel framework termed Cut-and-Paste for real-word semantic video editing under the guidance of text prompt and additional reference image. While the text-driven video editing has demonstrated remarkable ability to…
Grounding (i.e. localizing) arbitrary, free-form textual phrases in visual content is a challenging problem with many applications for human-computer interaction and image-text reference resolution. Few datasets provide the ground truth…
Recent advancements in image editing have utilized large-scale multimodal models to enable intuitive, natural instruction-driven interactions. However, conventional methods still face significant challenges, particularly in spatial…
Recent Vision-Language Pre-training (VLP) models have demonstrated significant advancements. Nevertheless, these models heavily rely on image-text pairs that capture only coarse and global information of an image, leading to a limitation in…
Layered image assets are widely used in real-world creative workflows, enabling non-destructive iteration and flexible re-composition. Recent advances in layered image generation and decomposition synthesize or recover layered…