NeurIPS 2023 Papers

The Stable Diffusion model is a prominent text-to-image generation model that relies on a text prompt as its input, which is encoded using the Contrastive Language-Image Pre-Training (CLIP). However, text prompts have limitations when it comes to incorporating implicit information from reference images. Existing methods have attempted to address this limitation by employing expensive training procedures involving millions of training samples for image-to-image generation. In contrast, this paper demonstrates that the CLIP model, as utilized in Stable Diffusion, inherently possesses the ability to instantaneously convert images into text prompts. Such an image-to-prompt conversion can be achieved by utilizing a linear projection matrix that is calculated in a closed form. Moreover, the paper showcases that this capability can be further enhanced by either utilizing a small amount of similar-domain training data (approximately 100 images) or incorporating several online training steps (around 30 iterations) on the reference images. By leveraging these approaches, the proposed method offers a simple and flexible solution to bridge the gap between images and text prompts. This methodology can be applied to various tasks such as image variation and image editing, facilitating more effective and seamless interaction between images and textual prompts.

Text-conditioned image editing has emerged as a powerful tool for editing images. However, in many situations, language can be ambiguous and ineffective in describing specific image edits. When faced with such challenges, visual prompts can be a more informative and intuitive way to convey ideas. We present a method for image editing via visual prompting. Given pairs of example that represent the "before" and "after" images of an edit, our goal is to learn a text-based editing direction that can be used to perform the same edit on new images. We leverage the rich, pretrained editing capabilities of text-to-image diffusion models by inverting visual prompts into editing instructions. Our results show that with just one example pair, we can achieve competitive results compared to state-of-the-art text-conditioned image editing frameworks.

Diffusion models have gained increasing attention for their impressive generation abilities but currently struggle with rendering accurate and coherent text. To address this issue, we introduce TextDiffuser, focusing on generating images with visually appealing text that is coherent with backgrounds. TextDiffuser consists of two stages: first, a Transformer model generates the layout of keywords extracted from text prompts, and then diffusion models generate images conditioned on the text prompt and the generated layout. Additionally, we contribute the first large-scale text images dataset with OCR annotations, MARIO-10M, containing 10 million image-text pairs with text recognition, detection, and character-level segmentation annotations. We further collect the MARIO-Eval benchmark to serve as a comprehensive tool for evaluating text rendering quality. Through experiments and user studies, we demonstrate that TextDiffuser is flexible and controllable to create high-quality text images using text prompts alone or together with text template images, and conduct text inpainting to reconstruct incomplete images with text. We will make the code, model and dataset publicly available.

Point cloud data collected in real-world applications are often incomplete. This is because they are observed from partial viewpoints, which capture only a specific perspective or angle, or due to occlusion and low resolution. Existing completion approaches rely on datasets of specific predefined objects to guide the completion of incomplete, and possibly noisy, point clouds. However, these approaches perform poorly with Out-Of-Distribution (OOD) objects, which are either absent from the dataset or poorly represented. In recent years, the field of text-guided image generation has made significant progress, leading to major breakthroughs in text guided shape generation. We describe an approach called SDS-Complete that uses a pre-trained text-to-image diffusion model and leverages the text semantic of a given incomplete point cloud of an object, to obtain a complete surface representation. SDS-Complete can complete a variety of objects at test time optimization without the need for an expensive collection of 3D information. We evaluate SDS-Complete on incomplete scanned objects, captured by real-world depth sensors and LiDAR scanners, and demonstrate that is effective in handling objects which are typically absent from common datasets.

Pre-trained text-to-image generative models can produce diverse, semantically rich, and realistic images from natural language descriptions. Compared with language, images usually convey information with more details and less ambiguity. In this study, we propose Learning from the Void (LfVoid), a method that leverages the power of pre-trained text-to-image models and advanced image editing techniques to guide robot learning. Given natural language instructions, LfVoid can edit the original observations to obtain goal images, such as "wiping" a stain off a table. Subsequently, LfVoid trains an ensembled goal discriminator on the generated image to provide reward signals for a reinforcement learning agent, guiding it to achieve the goal. The ability of LfVoid to learn with zero in-domain training on expert demonstrations or true goal observations (the void) is attributed to the utilization of knowledge from web-scale generative models. We evaluate LfVoid across three simulated tasks and validate its feasibility in the corresponding real-world scenarios. In addition, we offer insights into the key considerations for the effective integration of visual generative models into robot learning workflows. We posit that our work represents an initial step towards the broader application of pre-trained visual generative models in the robotics field. Our project page: https://lfvoid-rl.github.io/.

Existing score-distilling text-to-3D generation techniques, despite their considerable promise, often encounter the view inconsistency problem. One of the most notable issues is the Janus problem, where the most canonical view of an object (\textit{e.g}., face or head) appears in other views. In this work, we explore existing frameworks for score-distilling text-to-3D generation and identify the main causes of the view inconsistency problem---the embedded bias of 2D diffusion models. Based on these findings, we propose two approaches to debias the score-distillation frameworks for view-consistent text-to-3D generation. Our first approach, called score debiasing, involves cutting off the score estimated by 2D diffusion models and gradually increasing the truncation value throughout the optimization process. Our second approach, called prompt debiasing, identifies conflicting words between user prompts and view prompts using a language model, and adjusts the discrepancy between view prompts and the viewing direction of an object. Our experimental results show that our methods improve the realism of the generated 3D objects by significantly reducing artifacts and achieve a good trade-off between faithfulness to the 2D diffusion models and 3D consistency with little overhead. Our project page is available at~\url{https://susunghong.github.io/Debiased-Score-Distillation-Sampling/}.

We introduce Cap3D, an automatic approach for generating descriptive text for 3D objects. This approach utilizes pretrained models from image captioning, image-text alignment, and LLM to consolidate captions from multiple views of a 3D asset, completely side-stepping the time-consuming and costly process of manual annotation. We apply Cap3D to the recently introduced large-scale 3D dataset, Objaverse, resulting in 660k 3D-text pairs. Our evaluation, conducted using 41k human annotations from the same dataset, demonstrates that Cap3D surpasses human-authored descriptions in terms of quality, cost, and speed. Through effective prompt engineering, Cap3D rivals human performance in generating geometric descriptions on 17k collected annotations from the ABO dataset. Finally, we finetune Text-to-3D models on Cap3D and human captions, and show Cap3D outperforms; and benchmark the SOTA including Point·E, Shape·E, and DreamFusion.

Text-to-image generation has recently witnessed remarkable achievements. We introduce a text-conditional image diffusion model, termed RAPHAEL, to generate highly artistic images, which accurately portray the text prompts, encompassing multiple nouns, adjectives, and verbs. This is achieved by stacking tens of mixture-of-experts (MoEs) layers, i.e., space-MoE and time-MoE layers, enabling billions of diffusion paths (routes) from the network input to the output. Each path intuitively functions as a "painter" for depicting a particular textual concept onto a specified image region at a diffusion timestep. Comprehensive experiments reveal that RAPHAEL outperforms recent cutting-edge models, such as Stable Diffusion, ERNIE-ViLG 2.0, DeepFloyd, and DALL-E 2, in terms of both image quality and aesthetic appeal. Firstly, RAPHAEL exhibits superior performance in switching images across diverse styles, such as Japanese comics, realism, cyberpunk, and ink illustration. Secondly, a single model with three billion parameters, trained on 1,000 A100 GPUs for two months, achieves a state-of-the-art zero-shot FID score of 6.61 on the COCO dataset. Furthermore, RAPHAEL significantly surpasses its counterparts in human evaluation on the ViLG-300 benchmark. We believe that RAPHAEL holds the potential to propel the frontiers of image generation research in both academia and industry, paving the way for future breakthroughs in this rapidly evolving field. More details can be found on a webpage: https://raphael-painter.github.io/.

Compositional reasoning is a hallmark of human visual intelligence. Yet, despite the size of large vision-language models, they struggle to represent simple compositions by combining objects with their attributes. To measure this lack of compositional capability, we design Cola, a text-to-image retrieval benchmark to Compose Objects Localized with Attributes. To solve Cola, a model must retrieve images with the correct configuration of attributes and objects and avoid choosing a distractor image with the same objects and attributes but in the wrong configuration. Cola contains about 1.2k composed queries of 168 objects and 197 attributes on around 30K images. Our human evaluation finds that Cola is 83.33% accurate, similar to contemporary compositionality benchmarks. Using Cola as a testbed, we explore empirical modeling designs to adapt pre-trained vision-language models to reason compositionally. We explore 6 adaptation strategies on 2 seminal vision-language models, using compositionality-centric test benchmarks - Cola and CREPE. We find the optimal adaptation strategy is to train a multi-modal attention layer that jointly attends over the frozen pre-trained image and language features. Surprisingly, training multimodal layers on CLIP performs better than tuning a larger FLAVA model with already pre-trained multimodal layers. Furthermore, our adaptation strategy improves CLIP and FLAVA to comparable levels, suggesting that training multimodal layers using contrastive attribute-object data is key, as opposed to using them pre-trained. Lastly, we show that Cola is harder than a closely related contemporary benchmark, CREPE, since simpler fine-tuning strategies without multimodal layers suffice on CREPE, but not on Cola. However, we still see a significant gap between our best adaptation and human accuracy, suggesting considerable room for further research. Project page: https://cs-people.bu.edu/array/research/cola/

Automatically determining whether a text and a corresponding image are semantically aligned is a significant challenge for vision-language models, with applications in generative text-to-image and image-to-text tasks. In this work, we study methods for automatic text-image alignment evaluation. We first introduce SeeTRUE: a comprehensive evaluation set, spanning multiple datasets from both text-to-image and image-to-text generation tasks, with human judgements for whether a given text-image pair is semantically aligned. We then describe two automatic methods to determine alignment: the first involving a pipeline based on question generation and visual question answering models, and the second employing an end-to-end classification approach by finetuning multimodal pretrained models. Both methods surpass prior approaches in various text-image alignment tasks, with significant improvements in challenging cases that involve complex composition or unnatural images. Finally, we demonstrate how our approaches can localize specific misalignments between an image and a given text, and how they can be used to automatically re-rank candidates in text-to-image generation.

Generating controllable and photorealistic digital human avatars is a long-standing and important problem in Vision and Graphics. Recent methods have shown great progress in terms of either photorealism or inference speed while the combination of the two desired properties still remains unsolved. To this end, we propose a novel method, called DELIFFAS, which parameterizes the appearance of the human as a surface light field that is attached to a controllable and deforming human mesh model. At the core, we represent the light field around the human with a deformable two-surface parameterization, which enables fast and accurate inference of the human appearance. This allows perceptual supervision on the full image compared to previous approaches that could only supervise individual pixels or small patches due to their slow runtime. Our carefully designed human representation and supervision strategy leads to state-of-the-art synthesis results and inference time. The video results and code are available at https://vcai.mpi-inf.mpg.de/projects/DELIFFAS.

This paper presents a novel method to enhance the reliability of image classification models during deployment in the face of transient hardware errors. By utilizing enriched text embeddings derived from GPT-3 with question prompts per class and CLIP pretrained text encoder, we investigate their impact as an initialization for the classification layer. Our approach achieves a remarkable $5.5\times$ average increase in hardware reliability (and up to $14\times$) across various architectures in the most critical layer, with minimal accuracy drop ($0.3\%$ on average) compared to baseline PyTorch models. Furthermore, our method seamlessly integrates with any image classification backbone, showcases results across various network architectures, decreases parameter and FLOPs overhead, and follows a consistent training recipe. This research offers a practical and efficient solution to bolster the robustness of image classification models against hardware failures, with potential implications for future studies in this domain. Our code and models are released at https://github.com/TalalWasim/TextGuidedResilience.

In this work, we investigate the task of text-to-image (T2I) synthesis under the abstract-to-intricate setting, i.e., generating intricate visual content from simple abstract text prompts. Inspired by human imagination intuition, we propose a novel scene-graph hallucination (SGH) mechanism for effective abstract-to-intricate T2I synthesis. SGH carries out scene hallucination by expanding the initial scene graph (SG) of the input prompt with more feasible specific scene structures, in which the structured semantic representation of SG ensures high controllability of the intrinsic scene imagination. To approach the T2I synthesis, we deliberately build an SG-based hallucination diffusion system. First, we implement the SGH module based on the discrete diffusion technique, which evolves the SG structure by iteratively adding new scene elements. Then, we utilize another continuous-state diffusion model as the T2I synthesizer, where the overt image-generating process is navigated by the underlying semantic scene structure induced from the SGH module. On the benchmark COCO dataset, our system outperforms the existing best-performing T2I model by a significant margin, especially improving on the abstract-to-intricate T2I generation. Further in-depth analyses reveal how our methods advance.

Image restoration techniques, spanning from the convolution to the transformer paradigm, have demonstrated robust spatial representation capabilities to deliver high-quality performance.Yet, many of these methods, such as convolution and the Feed Forward Network (FFN) structure of transformers, primarily leverage the basic first-order channel interactions and have not maximized the potential benefits of higher-order modeling. To address this limitation, our research dives into understanding relationships within the channel dimension and introduces a simple yet efficient, high-order channel-wise operator tailored for image restoration. Instead of merely mimicking high-order spatial interaction, our approach offers several added benefits: Efficiency: It adheres to the zero-FLOP and zero-parameter principle, using a spatial-shifting mechanism across channel-wise groups. Simplicity: It turns the favorable channel interaction and aggregation capabilities into element-wise multiplications and convolution units with $1 \times 1$ kernel. Our new formulation expands the first-order channel-wise interactions seen in previous works to arbitrary high orders, generating a hierarchical receptive field akin to a Rubik's cube through the combined action of shifting and interactions. Furthermore, our proposed Rubik's cube convolution is a flexible operator that can be incorporated into existing image restoration networks, serving as a drop-in replacement for the standard convolution unit with fewer parameters overhead. We conducted experiments across various low-level vision tasks, including image denoising, low-light image enhancement, guided image super-resolution, and image de-blurring. The results consistently demonstrate that our Rubik's cube operator enhances performance across all tasks. Code is publicly available at https://github.com/zheng980629/RubikCube.

Object detection in aerial images is a growing area of research, with maritime object detection being a particularly important task for reliable surveillance, monitoring, and active rescuing. Notwithstanding astonishing advances of computer vision technologies, detecting ships and floating matters in these images are challenging due to factors such as object distance. What makes it worse is pervasive sea surface effects such as sunlight reflection, wind, and waves. Hyperspectral image (HSI) sensors, providing more than 100 channels in wavelengths of visible and near-infrared, can extract intrinsic information of materials from a few pixels of HSIs. The advent of HSI sensors motivates us to leverage HSIs to circumvent false positives due to the sea surface effects. Unfortunately, there are few public HSI datasets due to the high cost and labor involved in collecting them, hindering object detection research based on HSIs. We have collected and annotated a new dataset called ``Multi-Modal Ship and flOating matter Detection in Aerial Images (M$^{2}$SODAI),'', which includes synchronized image pairs of RGB and HSI data, along with bounding box labels for nearly 6,000 instances per category. We also propose a new multi-modal extension of the feature pyramid network called DoubleFPN. Extensive experiments on our benchmark demonstrate that fusion of RGB and HSI data can enhance mAP, especially in the presence of the sea surface effects.

The success of style-based generators largely benefits from style modulation, which helps take care of the cross-instance variation within data. However, the instance-wise stochasticity is typically introduced via regular convolution, where kernels interact with features at some fixed locations, limiting its capacity for modeling geometric variation. To alleviate this problem, we equip the generator in generative adversarial networks (GANs) with a plug-and-play module, termed as modulated transformation module (MTM). This module predicts spatial offsets under the control of latent codes, based on which the convolution operation can be applied at variable locations for different instances, and hence offers the model an additional degree of freedom to handle geometry deformation. Extensive experiments suggest that our approach can be faithfully generalized to various generative tasks, including image generation, 3D-aware image synthesis, and video generation, and get compatible with state-of-the-art frameworks without any hyper-parameter tuning. It is noteworthy that, towards human generation on the challenging TaiChi dataset, we improve the FID of StyleGAN3 from 21.36 to 13.60, demonstrating the efficacy of learning modulated geometry transformation. Code and models are available at https://github.com/limbo0000/mtm.

The pursuit of controllability as a higher standard of visual content creation has yielded remarkable progress in customizable image synthesis. However, achieving controllable video synthesis remains challenging due to the large variation of temporal dynamics and the requirement of cross-frame temporal consistency. Based on the paradigm of compositional generation, this work presents VideoComposer that allows users to flexibly compose a video with textual conditions, spatial conditions, and more importantly temporal conditions. Specifically, considering the characteristic of video data, we introduce the motion vector from compressed videos as an explicit control signal to provide guidance regarding temporal dynamics. In addition, we develop a Spatio-Temporal Condition encoder (STC-encoder) that serves as a unified interface to effectively incorporate the spatial and temporal relations of sequential inputs, with which the model could make better use of temporal conditions and hence achieve higher inter-frame consistency. Extensive experimental results suggest that VideoComposer is able to control the spatial and temporal patterns simultaneously within a synthesized video in various forms, such as text description, sketch sequence, reference video, or even simply hand-crafted motions. The code and models are publicly available at https://videocomposer.github.io.

Synthesizing images with user-specified subjects has received growing attention due to its practical applications. Despite the recent success in single subject customization, existing algorithms suffer from high training cost and low success rate along with increased number of subjects. Towards controllable image synthesis with multiple subjects as the constraints, this work studies how to efficiently represent a particular subject as well as how to appropriately compose different subjects. We find that the text embedding regarding the subject token already serves as a simple yet effective representation that supports arbitrary combinations without any model tuning. Through learning a residual on top of the base embedding, we manage to robustly shift the raw subject to the customized subject given various text conditions. We then propose to employ layout, a very abstract and easy-to-obtain prior, as the spatial guidance for subject arrangement. By rectifying the activations in the cross-attention map, the layout appoints and separates the location of different subjects in the image, significantly alleviating the interference across them. Using cross-attention map as the intermediary, we could strengthen the signal of target subjects and weaken the signal of irrelevant subjects within a certain region, significantly alleviating the interference across subjects. Both qualitative and quantitative experimental results demonstrate our superiority over state-of-the-art alternatives under a variety of settings for multi-subject customization.

Subject-driven text-to-image generation models create novel renditions of an input subject based on text prompts. Existing models suffer from lengthy fine-tuning and difficulties preserving the subject fidelity. To overcome these limitations, we introduce BLIP-Diffusion, a new subject-driven image generation model that supports multimodal control which consumes inputs of subject images and text prompts. Unlike other subject-driven generation models, BLIP-Diffusion introduces a new multimodal encoder which is pre-trained to provide subject representation. We first pre-train the multimodal encoder following BLIP-2 to produce visual representation aligned with the text. Then we design a subject representation learning task which enables a diffusion model to leverage such visual representation and generates new subject renditions. Compared with previous methods such as DreamBooth, our model enables zero-shot subject-driven generation, and efficient fine-tuning for customized subject with up to 20x speedup. We also demonstrate that BLIP-Diffusion can be flexibly combined with existing techniques such as ControlNet and prompt-to-prompt to enable novel subject-driven generation and editing applications. Implementations are available at: https://github.com/salesforce/LAVIS/tree/main/projects/blip-diffusion.