Related papers: 3DIS: Depth-Driven Decoupled Instance Synthesis fo…

The growing demand for controllable outputs in text-to-image generation has driven significant advancements in multi-instance generation (MIG), enabling users to define both instance layouts and attributes. Currently, the state-of-the-art…

We introduce the Multi-Instance Generation (MIG) task, which focuses on generating multiple instances within a single image, each accurately placed at predefined positions with attributes such as category, color, and shape, strictly…

We present a Multi-Instance Generation (MIG) task, simultaneously generating multiple instances with diverse controls in one image. Given a set of predefined coordinates and their corresponding descriptions, the task is to ensure that…

Multi-Instance Generation has advanced significantly in spatial placement and attribute binding. However, existing approaches still face challenges in fine-grained semantic understanding, particularly when dealing with complex textual…

This paper introduces MIDI, a novel paradigm for compositional 3D scene generation from a single image. Unlike existing methods that rely on reconstruction or retrieval techniques or recent approaches that employ multi-stage…

Precise spatial fidelity in Image-to-3D multi-instance generation is critical for downstream real-world applications. Recent work attempts to address this by fine-tuning pre-trained Image-to-3D (I23D) models on multi-instance datasets,…

While recent feed-forward 3D reconstruction models provide a strong geometric foundation for scene understanding, extending them to 3D instance segmentation typically relies on a disjointed "lift-and-cluster" paradigm. Grouping dense…

Class-agnostic 3D instance segmentation tackles the challenging task of segmenting all object instances, including previously unseen ones, without semantic class reliance. Current methods struggle with generalization due to the scarce…

We introduce Open3DIS, a novel solution designed to tackle the problem of Open-Vocabulary Instance Segmentation within 3D scenes. Objects within 3D environments exhibit diverse shapes, scales, and colors, making precise instance-level…

Conventional 3D instance segmentation methods rely on labor-intensive 3D annotations for supervised training, which limits their scalability and generalization to novel objects. Recent approaches leverage multi-view 2D masks from the…

Semi-Supervised Instance Segmentation (SSIS) aims to leverage an amount of unlabeled data during training. Previous frameworks primarily utilized the RGB information of unlabeled images to generate pseudo-labels. However, such a mechanism…

Image-conditioned generation methods, such as depth- and canny-conditioned approaches, have demonstrated remarkable abilities for precise image synthesis. However, existing models still struggle to accurately control the content of multiple…

Text-guided 3D shape generation remains challenging due to the absence of large paired text-shape data, the substantial semantic gap between these two modalities, and the structural complexity of 3D shapes. This paper presents a new…

Monocular 3D detection has drawn much attention from the community due to its low cost and setup simplicity. It takes an RGB image as input and predicts 3D boxes in the 3D space. The most challenging sub-task lies in the instance depth…

Open-set semantic mapping enables language-driven robotic perception, but current instance-centric approaches are bottlenecked by context-depriving and computationally expensive crop-based feature extraction. To overcome this fundamental…

Unlike closed-vocabulary 3D instance segmentation that is often trained end-to-end, open-vocabulary 3D instance segmentation (OV-3DIS) often leverages vision-language models (VLMs) to generate 3D instance proposals and classify them. While…

Text-to-image (T2I) generation models often struggle with multi-instance synthesis (MIS), where they must accurately depict multiple distinct instances in a single image based on complex prompts detailing individual features. Traditional…

Existing generative approaches for guided image synthesis of multi-object scenes typically rely on 2D controls in the image or text space. As a result, these methods struggle to maintain and respect consistent three-dimensional geometric…

We introduce 3D-SIS, a novel neural network architecture for 3D semantic instance segmentation in commodity RGB-D scans. The core idea of our method is to jointly learn from both geometric and color signal, thus enabling accurate instance…

Text-to-image diffusion generative models can generate high quality images at the cost of tedious prompt engineering. Controllability can be improved by introducing layout conditioning, however existing methods lack layout editing ability…