Related papers: InstructP2P: Learning to Edit 3D Point Clouds with…
Text-driven 3D scene editing has gained significant attention owing to its convenience and user-friendliness. However, existing methods still lack accurate control of the specified appearance and location of the editing result due to the…
Recent years have seen an explosion of work and interest in text-to-3D shape generation. Much of the progress is driven by advances in 3D representations, large-scale pretraining and representation learning for text and image data enabling…
Text-to-image (T2I) diffusion models, with their impressive generative capabilities, have been adopted for image editing tasks, demonstrating remarkable efficacy. However, due to attention leakage and collision between the cross-attention…
Recent advances in diffusion models have enabled high-quality generation and manipulation of images guided by texts, as well as concept learning from images. However, naive applications of existing methods to editing tasks that require…
We propose a local-to-global representation learning algorithm for 3D point cloud data, which is appropriate to handle various geometric transformations, especially rotation, without explicit data augmentation with respect to the…
Point clouds acquired by 3D scanning devices are often sparse, noisy, and non-uniform, causing a loss of geometric features. To facilitate the usability of point clouds in downstream applications, given such input, we present a…
Recently, leveraging pre-training techniques to enhance point cloud models has become a prominent research topic. However, existing approaches typically require full fine-tuning of pre-trained models to achieve satisfactory performance on…
We introduce P2P-NET, a general-purpose deep neural network which learns geometric transformations between point-based shape representations from two domains, e.g., meso-skeletons and surfaces, partial and complete scans, etc. The…
Recent advancements in instruction-based image editing and subject-driven generation have garnered significant attention, yet both tasks still face limitations in meeting practical user needs. Instruction-based editing relies solely on…
Along with the advancements in artificial intelligence technologies, image-to-point-cloud registration (I2P) techniques have made significant strides. Nevertheless, the dimensional differences in the features of points cloud…
We introduce Duoduo CLIP, a model for 3D representation learning that learns shape encodings from multi-view images instead of point clouds. The choice of multi-view images allows us to leverage 2D priors from off-the-shelf CLIP models to…
While diffusion models have achieved remarkable success in text-to-image generation, they encounter significant challenges with instruction-driven image editing. Our research highlights a key challenge: these models particularly struggle…
Large "instruction-tuned" language models (i.e., finetuned to respond to instructions) have demonstrated a remarkable ability to generalize zero-shot to new tasks. Nevertheless, they depend heavily on human-written instruction data that is…
Motivated by the intuition that one can transform two aligned point clouds to each other more easily and meaningfully than a misaligned pair, we propose CorrNet3D -- the first unsupervised and end-to-end deep learning-based framework -- to…
3D point clouds deep learning is a promising field of research that allows a neural network to learn features of point clouds directly, making it a robust tool for solving 3D scene understanding tasks. While recent works show that point…
Point cloud completion aims to recover the completed 3D shape of an object from its partial observation caused by occlusion, sensor's limitation, noise, etc. When some key semantic information is lost in the incomplete point cloud, the…
We introduce ShapeWords, an approach for synthesizing images based on 3D shape guidance and text prompts. ShapeWords incorporates target 3D shape information within specialized tokens embedded together with the input text, effectively…
3D dense captioning aims to describe individual objects by natural language in 3D scenes, where 3D scenes are usually represented as RGB-D scans or point clouds. However, only exploiting single modal information, e.g., point cloud, previous…
Recently, the impressive generative capabilities of diffusion models have been demonstrated, producing images with remarkable fidelity. Particularly, existing methods for the 3D object generation tasks, which is one of the fastest-growing…
Learning point clouds is challenging due to the lack of connectivity information, i.e., edges. Although existing edge-aware methods can improve the performance by modeling edges, how edges contribute to the improvement is unclear. In this…