Related papers: MoEdit: On Learning Quantity Perception for Multi-…
High-resolution image editing is essential for professional and creative applications, yet existing multimodal diffusion-based editors remain computationally inefficient and constrained to relatively low resolutions. Current approaches…
Image editing has advanced significantly with the development of diffusion models using both inversion-based and instruction-based methods. However, current inversion-based approaches struggle with big modifications (e.g., adding or…
Recent large-scale text-driven synthesis models have attracted much attention thanks to their remarkable capabilities of generating highly diverse images that follow given text prompts. Such text-based synthesis methods are particularly…
Multi-View Multi-Object Tracking (MV-MOT) aims to localize and maintain consistent identities of objects observed by multiple sensors. This task is challenging, as viewpoint changes and occlusion disrupt identity consistency across views…
Recent advances in large-scale text-to-image generation models have led to a surge in subject-driven text-to-image generation, which aims to produce customized images that align with textual descriptions while preserving the identity of…
Most real-world image editing tasks require multiple sequential edits to achieve desired results. Current editing approaches, primarily designed for single-object modifications, struggle with sequential editing: especially with maintaining…
The controllability of 3D object generation methods is achieved through input text. Existing text-to-3D object generation methods primarily focus on generating a single object based on a single object description. However, these methods…
We address the problem of multi-object 3D pose control in image diffusion models. Instead of conditioning on a sequence of text tokens, we propose to use a set of per-object representations, Neural Assets, to control the 3D pose of…
We formulate monocular depth estimation using denoising diffusion models, inspired by their recent successes in high fidelity image generation. To that end, we introduce innovations to address problems arising due to noisy, incomplete depth…
Adding Object into images based on text instructions is a challenging task in semantic image editing, requiring a balance between preserving the original scene and seamlessly integrating the new object in a fitting location. Despite…
Diffusion models have recently advanced video editing, yet controllable editing remains challenging due to the need for precise manipulation of diverse object properties. Current methods require different control signal for diverse editing…
While generative models produce high-quality images of concepts learned from a large-scale database, a user often wishes to synthesize instantiations of their own concepts (for example, their family, pets, or items). Can we teach a model to…
Recent advances in text-to-image diffusion models have enabled the photorealistic generation of images from text prompts. Despite the great progress, existing models still struggle to generate compositional multi-concept images naturally,…
Unsupervised object-centric learning methods allow the partitioning of scenes into entities without additional localization information and are excellent candidates for reducing the annotation burden of multiple-object tracking (MOT)…
The goal of image composition is merging a foreground object into a background image to obtain a realistic composite image. Recently, generative composition methods are built on large pretrained diffusion models, due to their unprecedented…
Instruction driven image editing with standard CLIP text encoders often fails in complex scenes with many objects. We present QL-Adapter, a framework for multiple object editing that tackles two challenges: enforcing object counts and…
Recent developments related to generative models have made it possible to generate diverse high-fidelity images. In particular, layout-to-image generation models have gained significant attention due to their capability to generate…
Instruction-based image editing holds immense potential for a variety of applications, as it enables users to perform any editing operation using a natural language instruction. However, current models in this domain often struggle with…
We propose an approach for curating multimodal data that we used for our entry in the 2023 DataComp competition filtering track. Our technique combines object detection and weak supervision-based ensembling. In the first of two steps in our…
Recent advances in text-to-image generation with diffusion models present transformative capabilities in image quality. However, user controllability of the generated image, and fast adaptation to new tasks still remains an open challenge,…