Papers › DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data

DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data

6 Jun 2024CVPR 2024 1arXiv:2406.04322archive 2025-07-28

Qihao Liu, Yi Zhang, Song Bai, Adam Kortylewski, Alan Yuille

We present DIRECT-3D, a diffusion-based 3D generative model for creating high-quality 3D assets (represented by Neural Radiance Fields) from text prompts. Unlike recent 3D generative models that rely on clean and well-aligned 3D data, limiting them to single or few-class generation, our model is directly trained on extensive noisy and unaligned `in-the-wild' 3D assets, mitigating the key challenge (i.e., data scarcity) in large-scale 3D generation. In particular, DIRECT-3D is a tri-plane diffusion model that integrates two innovations: 1) A novel learning framework where noisy data are filtered and aligned automatically during the training process. Specifically, after an initial warm-up phase using a small set of clean data, an iterative optimization is introduced in the diffusion process to explicitly estimate the 3D pose of objects and select beneficial data based on conditional density. 2) An efficient 3D representation that is achieved by disentangling object geometry and color features with two separate conditional diffusion models that are optimized hierarchically. Given a prompt input, our model generates high-quality, high-resolution, realistic, and complex 3D objects with accurate geometric details in seconds. We achieve state-of-the-art performance in both single-class generation and text-to-3D generation. We also demonstrate that DIRECT-3D can serve as a useful 3D geometric prior of objects, for example to alleviate the well-known Janus problem in 2D-lifting methods such as DreamFusion. The code and models are available for research purposes at: https://github.com/qihao067/direct3d.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 11 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 10 ran (9 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

qihao067/direct3d officialmentioned in papermentioned on GitHubpytorchMITSyntology: 11 samples, 10 ran (1 instrument-failed) · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

11 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
1ran · our draft was wrong
6ran
1unverified

Licence: 0 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from qihao067/direct3d. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

qihao067/direct3d official repository 11 samples, 10 ran (1 instrument-failed) · 1 unverified
biased_softplus in 5 papers lib/ops/activation.py ran fingerprinted MIT (permissive) · fb07704f3a4c0430 · report fixture: signature x:Tensor/2/float, bias:float/0/float · returned Tensor · level recorded 2026-09-24
extract_fields in 23 papers lib/core/nerf_utils.py ran MIT (permissive) · 3b86c5dc32a524c5 · report fixture: signature bound_min:list/1/float, bound_max:list/1/float, resolution:int/0/int, query_func:callable/0/?, S:int/0/int · returned ndarray · level recorded 2026-09-24
filter_img_2d lib/core/evaluation/metrics.py ran · our draft was wrong fingerprinted MIT (permissive) · 4309d8ca9039e8ae · report fixture: signature img:Tensor/4/float, kernel2d:Tensor/2/float · returned Tensor · level recorded 2026-09-24
gaussian_blur in 17 papers lib/core/evaluation/metrics.py ran MIT (permissive) · 9c85066b4c48bea0 · report fixture: signature img:Tensor/3/float, kernel_size:list/1/int, sigma:list/1/float · returned Tensor · level recorded 2026-09-24
get_encoder in 45 papers lib/ops/encoding.py ran MIT (permissive) · 6ac1e2c2159d77f9 · report fixture: signature encoding:str/0/str, input_dim:int/0/int, multires:int/0/int, degree:int/0/int, num_levels:int/0/int, level_dim:int/0/int, base_resolution:int/0/int, log2_hashmap_size:int/0/int, desired_resolution:int/0/int, align_corners:bool/0/bool, interpolation:str/0/str · returned tuple · level recorded 2026-09-24
get_ray_directions in 16 papers lib/core/nerf_utils.py ran MIT (permissive) · 7c19e54b9a1662ec · report fixture: signature h:int/0/int, w:int/0/int, focal:Tensor/1/float, center:Tensor/1/float, norm:bool/0/bool, device:NoneType/0/?, with_radius:bool/0/bool · returned tuple · level recorded 2026-09-24
get_rays in 39 papers lib/core/nerf_utils.py ran MIT (permissive) · 82f87998b3d6de72 · report fixture: signature directions:Tensor/3/float, c2w:Tensor/3/float, norm:bool/0/bool · returned tuple · level recorded 2026-09-24
load_intrinsics lib/datasets/direct3d.py ran · honoured contract MIT (permissive) · 271c72b090719abf · report fixture: signature path:str/0/str · returned tuple · level recorded 2026-09-24
load_pose in 6 papers lib/datasets/direct3d.py ran · honoured contract MIT (permissive) · 76c2c58e4e428303 · report fixture: signature path:str/0/str · returned Tensor · level recorded 2026-09-24
load_rot_angle lib/datasets/direct3d.py ran · honoured contract MIT (permissive) · 65bb7a9b22581bc7 · report fixture: signature path:str/0/str · returned Tensor · level recorded 2026-09-24
filter_img_2d_separate lib/core/evaluation/metrics.py unverified MIT (permissive) · f2f1d661c7cd1774 · report

Tasks

3D GenerationText to 3D

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DiffusionSET

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections